This paper presents AddrRaG, a retrieval-augmented framework designed for autonomous identification of delivery addresses under noisy and ambiguous conditions. AddrRaG integrates an enhanced encoder-based ensemble retrieval system with a fine-tuned large language model (LLM) for candidate validation, structured as a two-stage pipeline. Evaluated on a large-scale real-world French delivery dataset, AddrRaG achieves 97.4% identification accuracy and 99.4% safety rate, substantially outperforming baseline methods. The proposed approach balances retrieval efficiency with robust disambiguation, demonstrating its effectiveness for complex address matching tasks in operational transport settings. Complementary materials and details are available at: github.com/GeoRAG.

Federated learning (FL) offers a promising approach to improving the efficiency and privacy of Internet of Things (IoT) systems, particularly in environments where data is distributed across numerous devices. However, challenges remain in selecting the right FL model for specific applications, managing data privacy, and optimizing system performance. This paper evaluates four FL models - FedAvg, FedPer, FedProx, and FedSGD - against these challenges, focusing on their ability to optimize resource management, enhance data privacy, and reduce communication costs in real-time IoT settings. We provide a detailed comparison of their loss rates, execution times, and scalability, offering valuable insights into how each model performs under varying conditions. By addressing these key issues, our work contributes to the effective deployment of FL in distributed IoT systems, guiding the selection of the most suitable model for diverse applications.

As the proliferation of devices on the Internet of Things (IoT) accelerates, the need for efficient communication technologies becomes even more critical, particularly in rural and agricultural regions where connectivity challenges are more pronounced. LoRaWAN, a Low Power Wide Area Network (LPWAN) technology, offers a promising solution due to its long-range capabilities, low power consumption, and cost-effectiveness. However, optimizing gateway placement within LoRaWAN networks remains a key challenge, especially when considering factors such as terrain coverage, node distribution, gateway capabilities, and the need for efficient communication. This paper presents a novel simulation-based approach to optimize LoRaWAN gateway placement using the FLoRa framework integrated with OMNeT++. Our methodology incorporates network performance simulation, optimization data analysis, and K-means clustering to strategically place gateways while addressing constraints such as node separation and gateway capacity. The results demonstrate significant improvements in network coverage, energy efficiency, and a reduction in the number of gateways required, offering a practical solution for the deployment of scalable and efficient IoT networks in resource-constrained environments, particularly rural and agricultural settings.

LoRaWAN (Long-Range Wide Area Network) is a key protocol for large-scale IoT applications, but optimizing the placement of gateways remains a significant challenge, balancing network coverage, resource efficiency, and computational cost. The placement of the gateway directly impacts the performance, scalability, and reliability of the network, which makes it essential for efficient IoT network design. Although clustering algorithms show promise in optimizing gateway placement, each face limitations related to scalability, computational demands, and adaptability to changing network conditions. This paper evaluates three clustering algorithms, that is, K-Means, MeanShift, and DBSCAN, to optimize the placement of the LoRaWAN gateway. We examine their effects on network coverage, gateway usage, and computational efficiency in networks of varying sizes. Our results demonstrate that DBSCAN is highly scalable and efficient but struggles with coverage optimization. MeanShift offers the best coverage, but is computationally expensive, while K-Means provides a balanced solution for medium-sized networks.

Training and Inferencing phases of Machine Learning (ML) are compute-intensive often requiring cloud-hosted resources. However real-time needs of Internet of Things (IoT) applications and variable and long latencies between the edge and the cloud require new ways to exploit clusters of edge devices and decentralized federated approaches to ML training/in-ferencing. Federated Machine Learning (FedML) is however fraught with many challenges including the need to discover resources heterogeneity in resource types leading to non-uniform execution times among cluster members increased incidences of failures and network disconnectivity leading to consistency issues preserving privacy of data the type of distributed ML algorithm used to require its availability on the chosen resources and many others. To address this plethora of challenges this early stage research surveys seven FedML approaches to investigate the feasibility of a privacy-preserving edge-centric distributed ML solutions on edge devices. We also discuss the open issues FedML still faces. Finally we highlight the trends and prospects towards future on-device and Edge AI.

LoRaWAN protocol has shown promising benefits to diverse IoT verticals by enabling information exchange over long distances via their gateways and enable full sensor coverage while maintaining low power consumption, a long battery lifetime, and transmission across large geographic distances. However, the planning, deployment, and management of LoRaWAN roll-outs are challenging. While several path loss models have been proposed to improve the transmission of packets between sensor nodes and remote gateways, the quality of the data transmission becomes a concern. In this paper, we study four path loss propagation models and test them in a simulation environment in order to identify which model offers better transmission and coverage qualities.The results of experiments show how the Free Space Path Loss (FSPL) model achieves 68% better accuracy performances against baseline propagation models in terms of signal propagation and full sensors’ coverage.

To improve the accuracy of an RNN when processing sparse and irregular multivariate clinical time series, we introduce two stacked deep learning models built on top of it, namely Padd-GRU and Alignment-driven Neural Network (ALNN). The Padd-GRU performs data-driven padding and imputation to obtain equal-length univariate and fill-in missing values, respectively. Then, the ALNN component transforms the resulting padded irregular multivariate clinical time series into a pseudo-aligned (or pseudo-regular) latent multivariate time series. We use the MIMIC-3 and PhysioNet databases to evaluate and compare our model to the state-of-the-art models on the mortality prediction task.

The rapid evolution of digital technologies has given rise to the concept of Digital Twin, a dynamic, virtual representation of physical systems, processes, and environments. This special issue delves into the transformative potential of Digital Twins in the realm of future networks and emerging Internet of Things (IoT) applications. By integrating advanced simulation, real-time data analytics, and machine learning, Digital Twins offer unprecedented opportunities for optimizing network performance, enhancing predictive maintenance, and enabling smarter IoT solutions. The articles in this issue explore a variety of topics, including the development and implementation of Digital Twins for next-generation communication networks, the role of artificial intelligence in enhancing the fidelity and utility of Digital Twins, and the application of these technologies in diverse IoT domains such as smart cities, healthcare, industrial automation, and environmental monitoring. Emphasis is placed on innovative methodologies, case studies, and experimental results that highlight the practical benefits and challenges associated with deploying Digital Twins in real-world scenarios. Through this special issue, we aim to provide a comprehensive overview of the current state of research and development in Digital Twins, underscore the technological advancements driving their adoption, and discuss future directions and open research questions. This collection of works serves as a valuable resource for researchers, practitioners, and policymakers interested in harnessing the power of Digital Twins to revolutionize network infrastructures and IoT ecosystems.

The purpose of this work is to present the recent results that we have obtained on a new job board recommendation system. Firstly, the job applicant clickstreams history on various job boards are stored in a large learning database, and then represented as time series. Secondly, a deep neural network is trained to predict future values of the clicks on the job boards. Third, and in a parallel way, dimensionality reduction techniques are used to transform the clicks multivariate numerical time series into temporal symbolic sequences. Ngrams are then used to predict future symbols for each sequence. Finally, a list of top ranked job boards are kept by maximizing the clickstreams forecasting in both representations. Our experiments are tested on a real dataset, coming from a job-posting database of an industrial partner. The promising results have shown that using deep learning, the recommendation system outperforms standard multivariate models.

The main limitations of the existing high level image retrieval approaches concern the high dependance on an external reliable resource (domain ontologies, learning sets, etc.) and a model for mapping semantic and visual information. In this paper, we propose an image retrieval system integrating semantic and visual features. The idea is to automatically build a modular ontology for semantic information and organize visual features in a graph-based model. Both elements are then combined together in a same component called “pattern” used for retrieval. The system has been implemented and the obtained results show that our proposal enables an improvement in the retrieval task.