1 IEEE Latin American Conference on Internet of Things
April 23-25, 2025 - FORTALEZA | BRAZIL
st
An IEEE IoT TC Flagship Conference


Organized by:

.jpg)
KEYNOTE & PLENARY SPEAKERS
Giancarlo Fortino, University of Calabria, Italy
From Digital Twins to Generative Digital Twins: Towards a Novel Approach in the IoT Edge-Cloud Continuum
Digital Twins (DTs) are software replicas that not only mirrors physical entities but can also proactively predict, control, optimize and simulate their behavior. Born in the manufacturing sector, this concept after an initial hype stayed untouched for decades. The rise of Internet of Things (IoT) and Artificial Intelligence (AI) enabled DT, respectively, to exchange real-world data and to fully exploit it for fulfilling its own goals. Very recently, Gener-ative AI (Gen-AI) methods started being sporadically applied to DT in different contexts and with different targets. In this talk, starting from our experiences on design, implementation and evaluation of DTs and, more recently, of Opportunistic DTs, we first provide a definition for the Generative DT (GDT) which embraces main distinctive aspects and potential of current and future Gen-Al-aided DTs. In particular, we disclose the role of Gen-AI in conciliating the model- and the data-driven approach for the development of DTs. Then, we analyze the added value of main Gen-AI architectures for maximizing the performance of DTs operating in the IoT domain and deployed in the edge-cloud continuum. Finally, we illustrate the potential of a GDT in emblematic Smart City scenarios through a use case involving the prediction of vehicles' trajectories when, due to uncontrolled events, only partial information is accessible. The outlined solution conciliates accuracy and explainability in the trajectory prediction with overall system robustness and effectiveness.
Jorge Fernandes, INESC-ID, Portugal
Energy-Efficient Circuit Design for IoT Applications
Internet-of-Things comprise many applications with the common goal to connect all “things”, with computers (internet) and people (communications). This talk addresses IoT systems that have to be very energy efficient while still having the capability to locally process signals, either in analog or digital domain, and communicate wirelessly. It will cover techniques and strategies used in the design of analog, digital and RF circuits: These techniques will be illustrated with use cases.
Paulo Maciel, Federal University of Pernambuco (UFPE), Brazil
Pursuing Reliable IoT Systems: Balancing Complexity and Representativeness in Stochastic Modeling
IoT systems are the backbone of modern digital infrastructure, making their reliability and availability critical. Failures in distributed IoT networks can disrupt essential services, from smart cities to industrial automation. Effectively modeling and predicting these failures requires balancing accuracy and scalability. In this talk, we discuss stochastic modeling as a powerful approach to evaluating and improving IoT system reliability and availability. We examine state-based models (e.g., Markov Chains, Stochastic Petri Nets) and structure-based models (e.g., Fault Trees, Reliability Block Diagrams) for assessing failure modes, resilience, and recovery strategies. Key aspects such as scalability, time-dependent behavior, and sensitivity analysis will also be addressed. Combining stochastic numerical analysis, simulation, and analytical modeling, we discuss a practical framework for IoT design, capacity planning, and risk assessment. Additionally, we explore emerging research trends, including LLM reliability modeling, the analysis of complex, heterogeneous IoT ecosystems, and the use of both academic and commercial tools for stochastic modeling and evaluation.