Wildfires pose significant risks to ecosystems, human lives, and infrastructure, necessitating advanced predictive tools to mitigate their impacts. This study presents a machine learning-based framework for wildfire susceptibility mapping (WSM), designed as a predictive tool for wildfire occurrence. Using geographical information systems (GIS), a comprehensive dataset was developed by combining fourteen critical factors, including climatic, topographic, vegetation, and human activity data, from diverse sources. Four ML methods—Random Forest (RF), Support Vector Machine (SVM), Neural Network (NN), and XGBoost—were applied and compared. The results show that the XGBoost model (with an AUC of 0.96) generated the best susceptibility map. Validation using 2024–2025 fire occurrences (MODIS and Protection Civile data) showed that 87.73% of fire events were correctly captured within high and very high susceptibility zones, confirming the robustness of the proposed model. Feature importance analysis revealed that human activities, precipitation, and temperature were the most influential in wildfire prediction. These findings provide valuable insights into wildfire dynamics and contribute to the development of more effective fire prevention and mitigation strategies.
The use of UML Statecharts for modeling dynamic behaviors of systems is very widespread. UML Statechart diagrams support developers by means of graphical notation, but the lack of formal semantics for this diagram makes the detection of errors and behavioral inconsistencies difficult. On the other hand, the specification language LOTOS has been proved to be an essential technique for specifying and verifying distributed and communicating systems. However, the strong and obscure textual algebraic notation of LOTOS makes its utilization in software development an onerous and complex task. In the order to combine UML Statecharts with LOTOS for the formal specification and verification of system behaviors, we propose in this paper an approach and a tool environment to automatically generate behavioral LOTOS expressions from UML Statechart diagrams. The approach uses the meta-modeling tool AToM3.
Recently, Software-Defined Networks (SDNs) paradigm became a very interesting area for both researchers in academia and executive-boards in industry. The main goals of SDN are to improve the network performances, to allow more flexibility in controlling and managing networks and to enrich the network services via customizable network applications. In order to migrate, partially or fully, from a traditional network toward an SDN network, the network administrators are required to guarantee the consistency of the IP addressing scheme along with the routing plan. This is to fulfill a safely transit, responding to the business or research needs. In this paper, we present a new approach allowing to restore automatically the routing plan from traditional networks based on extending a topology discovery algorithm. The gathered data are then used to configure automatically the SDN routing applications through the exposed REST APIs. The proposed solution ensures a seamless and reliable layer-three migration, which saves time and prevents human errors.
1 January 2018 in International Journal of Embedded Systems
The increasing complexity and widespread use of complex and critical systems require advanced techniques and tools to address their specification, verification and validation. The goal of this paper is to integrate two standard languages (UML and LOTOS) for the specification, verification and validation of dynamic behaviours of critical systems. The main purpose of this integration is to take benefits of the ease-of-use of the graphical notation of UML in system modelling and the formal notation of LOTOS in system verification. In this paper, we propose a graph transformation-based approach to generate automatically LOTOS specifications from UML dynamic models. This approach enables developers, in one hand to model the behaviours of systems using graphical UML statechart and communication diagrams, and in the other hand to generate automatically verifiable LOTOS specifications. The proposed approach is automated using AToM
The use of UML Statechart and Communication diagrams for modeling dynamic behaviors of systems is very widespread. UML diagrams support developers by means of visual conceptual illustrations. However, the lacks of firm semantics for these diagrams make the detection of errors and behavioral inconsistencies difficult. On the other hand, the specification language LOTOS has been proved to be a powerful technique for specifying and verifying systems behaviors. Although LOTOS language allows developers to create rigorous and verifiable specifications, it uses textual algebraic notation which makes its utilization in software development an onerous and complex task. In the order to benefit of the advantages of UML diagrams and LOTOS language for the formal specification and verification of dynamic behaviors of systems, we propose an approach to generate LOTOS specifications from UML Statechart and Communication diagrams. This approach allows developers to model system behaviors using visual UML diagrams and then generates their equivalent LOTOS specifications for the verification purpose. The approach is automated using the meta-modeling tool AToM3.
23 May 2026 in Journal of Network and Systems Management