1,721,177 research outputs found
METODO E SISTEMA PER PREVEDERE IL FALLIMENTO DI UN’ENTITÀ MONITORATA
Full text linkLa presente invenzione riguarda un metodo (100, 200) per predire un malfunzionamento di un’entità (4). In particolare, l’entità (4) è caratterizzata da una pluralità di parametri. Il metodo (100, 200) prevede di predire (200) un malfunzionamento dell’entità (4) mediante un sistema di intelligenza artificiale (1) cui sono forniti dati relativi ai parametri dell’entità (4), in cui il sistema di intelligenza artificiale (1) è allenato mediante dei dati di allenamento.
Vantaggiosamente, i dati di allenamento sono selezionati secondo i seguenti passi:
a. acquisire (101-106) un insieme di dati di allenamento, laddove l’insieme di dati di allenamento comprende una pluralità di gruppi di dati di entità, ciascun gruppo di dati di entità comprendendo valori riferiti a parametri
caratteristici di una rispettiva entità di allenamento,
b. selezionare (107) dati di entità compresi in gruppi di dati di entità di un primo sottoinsieme di entità di allenamento dell’insieme di dati di allenamento,
c. allenare (109) il sistema di intelligenza artificiale mediante i dati di entità del primo sottoinsieme di entità di allenamento selezionati,
d. determinare (112) una distribuzione delle probabilità di malfunzionamento delle entità di allenamento dell’insieme di dati di allenamento, eseguendo il
sistema di intelligenza artificiale (1) allenato con i dati di entità del primo sottoinsieme di entità di allenamento,
e. determinare (113) i dati di allenamento selezionando dati di entità di entità di allenamento di un secondo sottoinsieme di entità di allenamento dell’insieme
di dati di allenamento in modo tale che il secondo sottoinsieme di entità di allenamento presenti una distribuzione delle probabilità di
malfunzionamento uguale a quella calcolata al punto d
Parcel delivery in urban areas: opportunities and threats for the mix of new business models and technologies
No full textIn recent years, freight transportation and parcel delivery became key activities in the economy of the urban areas. However, the different inefficiencies and externalities affecting the last mile segment lead operators and local administrations to make freight distribution more sustainable and competitive, by introducing new business models, integrating disruptive technologies (e.g., electric vehicles and cargo-bikes) and small consolidation points (e.g., mobile depot and lockers). Hence, this paper faces the interesting challenge concerning the integration of different technologies from both business and operational perspectives, with a twofold goal. First, we identify the synergies and conflicts between the actors involved in the urban parcel delivery. Second, we present a simulation-optimization framework to assess multi-technology policies for the management of last mile delivery in urban areas and we apply it to the city of Turin (Italy). According to our results, some insights can be derived. First, Urban logistics are complex problems where applying a structured analysis methodology able to mix qualitative and quantitative methods leads to better solutions compared to the ones in literature. Second, mixing the different options can lead to a significate reduction of externalities, but this process must be governed by policies able to avoid the conflicts between the actors in the system
New solution approaches for the capacitated supplier selection problem with total quantity discount and activation costs under demand uncertainty
Full text linkA Machine Learning-based DSS for mid and long-term company crisis prediction
Full text linkIn the field of detection and prediction of company defaults and bankruptcy, significant effort has been devoted to evaluating financial ratios as predictors using statistical models and machine learning techniques. This problem becomes crucially important when financial decision-makers are provided with predictions on which to act, based on the output of prediction models. However, research has shown that such predictors are sufficiently accurate in the short-term, with the focus mainly directed towards large and medium-large companies. In contrast, in this paper, we focus on mid- and long-term bankruptcy prediction (up to 60 months) targeting small and/or medium enterprises. The key contribution of this study is a substantial improvement of the prediction accuracy in the short-term (12 months) using machine learning techniques, compared to the state-of-the-art, while also making accurate mid- and long-term predictions (measure of the area under the ROC curve of 0.88 with a 60 month prediction horizon). Extensive computational tests on the entire set of companies in Italy highlight the efficiency and accuracy of the developed method, as well as demonstrating the possibility of using it as a tool for the development of strategies and policies for entire economic systems. Considering the recent COVID-19 pandemic, we show how our method can be used as a viable tool for large-scale policy-making
Diffusion of Connected, Communicative and Automated Mobility systems: an agent-based model
No full textConnected, Communicating and Automated Mobility
(CCAM) systems are a key component of the future of
smart cities. Providing tools to understand and forecast their
diffusion will facilitate the design and deployment of a much
needed technology, improving efficiency and sustainability of our
urban environments. In this paper, the authors present an agentbased
model for the diffusion in a metropolitan area of such a
service, and discuss its features and potentialities. The data used
to inform the model have been collected within the context of the
SINFONICA project, the flagship European-funded project that
aims to foster the diffusion of CCAM systems in Europe. The
agents in the model behave accordingly to transportation-related
attributes that define their habits as well as consumer-related
attributes that define their preferences and technological attitude.
We discuss two scenarios, with different performance levels of
the CCAM service that produce qualitatively different diffusion
patterns. The proposed ABM represents a valuable tool for city
planners and technology developers invested in the creation of
smart cities
New Solution Approaches for the Capacitated Supplier Selection Problem with Total Quantity Discount and Activation Costs under Demand Uncertainty
No full textBarriers to Web3 Technologies in Museums: A Qualitative Study in Turin
No full textThe museum sector is undergoing a significant digital transformation, accelerated by the COVID-19 pandemic, which exposed vulnerabilities such as revenue losses and reduced visitor engagement. Emerging Web3 technologies, including blockchain and Non-Fungible Tokens (NFTs), offer potential solutions for monetization, visitor engagement, and accessibility. However, adoption in Italian museums remains limited. This study explores the barriers to Web3 technology adoption from an institutional perspective, using qualitative interviews with 23 museum professionals, including directors and curators.
Key findings reveal multifaceted challenges, including skepticism about the added value of NFTs, perceived technological complexity, financial constraints, and regulatory uncertainties related to copyright and data protection. Cultural concerns also emerged, with some stakeholders fearing that digital innovations might compromise museums' traditional roles or lead to excessive commercialization. The study aligns these themes with the Unified Theory of Acceptance and Use of Technology (UTAUT), extending the model to include sector-specific factors.
The research highlights the tension between innovation and tradition in museums, emphasizing the need for compelling use cases, robust regulatory guidelines, and dedicated funding to facilitate adoption. By contextualizing Web3 adoption within UTAUT, this study provides a theoretical foundation for future empirical investigations and practical insights for museums navigating digital transformation. The findings underscore the importance of balancing technological advancement with cultural preservation, ensuring that digital tools enhance rather than overshadow the core mission of museums as custodians of heritage and education. This study contributes to a broader debate on technology adoption in cultural institutions, particularly in contexts with strong historical traditions such as Italy
The multi-path Traveling Salesman Problem with stochastic travel costs
Full text linkGiven a set of nodes, where each pair of nodes is connected by several paths and each path shows a stochastic travel cost with unknown distribution, the multipath Traveling Salesman Problem with stochastic travel costs aims at finding an
expected minimum Hamiltonian tour connecting all nodes. Under a mild assumption on the unknown probability distribution a deterministic approximation of the
stochastic problem is given. The comparison of such approximation with a Montecarlo simulation shows both the accuracy and the eciency of the deterministic approximation, with a mean percentage gap around 2% and a reduction of the computational times of two orders of magnitude
A Stochastic Programming Approach for the Capacitated Supplier Selection Problem with Total Quantity Discount and Activation Costs
No full text- …
