The interconnected and heterogeneous nature of the next-generation Electrical Grid (EG), widely known as Smart Grid (SG), bring severe cybersecurity and privacy risks that can also raise domino effects against other Critical Infrastructures (CIs). In this paper, we present an Intrusion Detection System (IDS) specially designed for the SG environments that use Modbus/Transmission Control Protocol (TCP) and Distributed Network Protocol 3 (DNP3) protocols. The proposed IDS called MENSA (anoMaly dEtection aNd claSsificAtion) adopts a novel Autoencoder-Generative Adversarial Network (GAN) architecture for (a) detecting operational anomalies and (b) classifying Modbus/TCP and DNP3 cyberattacks. In particular, MENSA combines the aforementioned Deep Neural Networks (DNNs) in a common architecture, taking into account the adversarial loss and the reconstruction difference. The proposed IDS is validated in four real SG evaluation environments, namely (a) SG lab, (b) substation, (c) hydropower plant and (d) power plant, solving successfully an outlier detection (i.e., anomaly detection) problem as well as a challenging multiclass classification problem consisting of 14 classes (13 Modbus/TCP cyberattacks and normal instances). Furthermore, MENSA can discriminate five cyberattacks against DNP3. The evaluation results demonstrate the efficiency of MENSA compared to other Machine Learning (ML) and Deep Learning (DL) methods in terms of Accuracy, False Positive Rate (FPR), True Positive Rate (TPR) and the F1 score.

Modern Healthcare cyberphysical systems have begun to rely more and more on distributed AI leveraging the power of Federated Learning (FL). Its ability to train Machine Learning (ML) and Deep Learning (DL) models for the wide variety of medical fields, while at the same time fortifying the privacy of the sensitive information that are present in the medical sector, makes the FL technology a necessary tool in modern health and medical systems. Unfortunately, due to the polymorphy of distributed data and the shortcomings of distributed learning, the local training of Federated models sometimes proves inadequate and thus negatively imposes the federated learning optimization process and in extend in the subsequent performance of the rest Federated models. Badly trained models can cause dire implications in the healthcare field due to their critical nature. This work strives to solve this problem by applying a post-processing pipeline to models used by FL. In particular, the proposed work ranks the model by finding how fair they are by discovering and inspecting micro-Manifolds that cluster each neural model's latent knowledge. The produced work applies a completely unsupervised both model and data agnostic methodology that can be leveraged for general model fairness discovery. The proposed methodology is tested against a variety of benchmark DL architectures and in the FL environment, showing an average 8.75% increase in Federated model accuracy in comparison with similar work.

In vitro fertilization (IVF) is a well-established and efficient assisted reproductive technology (ART). However, it requires a series of costly and non-trivial procedures, and the success rate still needs improvement. Thus, increasing the success rate, simplifying the process, and reducing costs are all essential challenges of IVF. These can be addressed by integrating artificial intelligence techniques, like deep learning (DL), with several aspects of the IVF process. DL techniques can help extract important features from the data, support decision making, and perform several other tasks, as architectures can be adapted to different problems. The emergence of AI in the medical field has seen a rise in DL-supported tools for embryo selection. In this work, recent advances in the use of AI and DL-based embryo selection for IVF are reviewed. The different architectures that have been considered so far for each task are presented. Furthermore, future challenges for artificial intelligence-based ARTs are outlined.

This study introduces an innovative, resource-efficient architecture that incorporates advanced technologies to create a lightweight, flexible, and scalable framework for remote and limited data collecting and processing in next-generation Internet of Things (IoT) applications. It specifically proposes an integrated Federated LoRaWAN (LoRA-FL) system that combines hierarchical, privacy-preserving Federated Learning (FL), Knowledge Distillation (KD), and a customised Medium Access Control (MAC) protocol, identified as FCA-LoRa, to address the significant limitations of LoRaWAN networks. These encompass strict duty cycle rules, restricted bandwidth, and energy limitations, elements that conventionally hinder the implementation of intelligent IoT devices in rural or isolated settings. The proposed architecture features a hierarchical FL approach enabling multi-tier Artificial Intelligence (AI) model aggregation across edge nodes, gateways, and a central server. The effectiveness of the proposed system is confirmed by two practical applications, smart agriculture and smart livestock farming, which exemplify standard situations for far-edge intelligence. The results indicate that the distilled model consistently attains over 90% packet delivery success, illustrating the architecture’s capacity to provide scalable and energy-efficient intelligence at the edge. This research addresses a significant gap in previous studies that frequently examine FL, communication optimisation, and model compression independently. This study offers a comprehensive, implementable approach that tackles model scalability, and network-layer issues within a cohesive architecture, enhancing the practical implementation of AI-driven IoT deployments over LoRaWAN.

Remote sensing stands out as one of the most widely used operations in the field. In this research area, UAVs offer full coverage of large cultivation areas in a few minutes and provide orthomosaic images with valuable information based on multispectral cameras. Especially for orchards, it is helpful to isolate each tree and then calculate the preferred vegetation indices separately. Thus, tree detection and crown extraction is another important research area in the domain of Smart Farming. In this paper, we propose an innovative tree detection method based on machine learning, designed to isolate each individual tree in an orchard. First, we evaluate the effectiveness of Detectron2 and YOLOv8 object detection algorithms in identifying individual trees and generating corresponding masks. Both algorithms yield satisfactory results in cherry tree detection, with the best F1-Score up to 94.85%. In the second stage, we apply a method based on OTSU thresholding to improve the provided masks and precisely cover the crowns of the detected trees. The proposed method achieves 85.30% on IoU while Detectron2 gives 79.83% and YOLOv8 has 75.36%. Our work uses cherry trees, but it is easy to apply to any other tree species. We believe that our approach will be a key factor in enabling health monitoring for each individual tree.

In the field of Smart Agriculture, accurate time series forecasting is essential for farmers to gather and evaluate relevant information about various aspects of their work, such as the management of harvests, livestock, crops, water and soil. One commonly used method for trend forecasting in time series is the Long Short Term Memory (LSTM) Recurrent Neural Network (RNN) model, due to its ability to retain context for longer periods and enhance performance in context-intensive tasks. To further improve the results, the use of Federated Learning (FL) can be implemented, allowing multiple data providers to simultaneously train on a shared model while preserving data privacy. In this study, a Centralised Federated Learning System (CFLS) is leveraged, that implements and evaluates the efficacy of FL in smart agriculture through the use of datasets produced by such infrastructures. The system receives data from multiple clients and creates an optimised global model through model federation. Consequently, the federated approach is compared with the conventional local training to explore the potential of FL in real-time forecasting for the Smart Farming sector.