Distributed collaborative machine learning techniques enable the training of intelligent models while preserving user data privacy. However, in reality, training a large-scale and intricate model on resource-constrained devices such as Unmanned Aerial Vehicles (UAVs) is unfeasible. In this context, lightweight and resource-efficient deep learning techniques are required. This work first suggests a new resource-aware distributed framework, SFMec, in the context of a UAV power consumption scenario. The framework is evaluated and compared with other distributed frameworks, including FedMec, a federated learning-based approach, to assess its performance across different system architectures and resource management strategies. The results obtained demonstrate that SFMec has the potential to conserve more than 50% of the storage space occupied by FedMec, making it more attractive for devices with limited resources. Then, a novel architecture, denoted as SFMecLite, is introduced to minimize the interactions between SFMec entities. Furthermore, an enhanced version of SFMecLite is also presented that greatly outperforms FedMec and reduces the computational and communication costs in SFMec without compromising learning performance.

Brain computer interface (BCI) enables the brain to directly control an external device by converting neural signals into actionable outputs. However, effective real-time translation of brain activity strongly depends on the quality of neural communication between the brain and the external device. 6G is the next generation of wireless communication, expected to provide unprecedented levels of data rates, data security, and automation capabilities. In this context, integrating 6G into BCI systems would not only enhance the performance of brain-device communication, but would also create new opportunities for innovative applications. This work provides a comprehensive study on how BCI technology can be built effectively on top of 6G wireless networks by introducing several technical aspects and use cases. We first provide an overview of BCI and 6G, following their progression from early development to convergence through cognitive communication and advanced neural interfaces. We then highlight the need for the upcoming 6G systems toward BCI technology in every aspect, including 6G technologies such as intelligent edge and zero-touch networks, and 6G use cases such as digital twin, immersive communication, and internet of minds. Furthermore, we identify key technical challenges, open issues, and future research directions related to the 6G-enabled BCI paradigm.

Respiratory diseases represent a significant health concern that attracts scientists and health professionals due to their impact on public health. Various techniques are used to identify respiratory conditions, from diagnosis to therapy, such as Computer Tomography (CT) scans and Chest X-ray (CXR) images. However, these methods require expert radiologists for manual examination, posing time challenges. This is especially critical during a pandemic, where swift detection and early treatment are paramount. In this regard, an AI-based diagnostic system for automatic identification would play a major role, particularly regarding the analysis of patient cough patterns. Coughs, as a diagnostic cue, provide distinctive information about glottis behavior related to different respiratory pathological cases. This work proposes a comparative investigation of respiratory disease detection techniques using cough sounds, with COVID-19 as a case study. Our study involves the application of three distinct models: a Convolutional Neural Network (CNN) model, a CNN-Support Vector Machine (CNN-SVM) hybrid model, and a transfer learning-based model. We methodically evaluate different model architectures, ranging from custom-built networks to pre-trained deep models, applying spectrogram or Mel-Frequency Cepstral Coefficients (MFCC) in transfer learning-based feature extraction, to determine which is the best approach in terms of accuracy, precision, recall, F1-score, and loss. The experimental findings highlight the superior performance of transfer learning and MFCC feature extraction upon deep learning results using CNN and CNN-SVM with best validation accuracies ranging from 99.55% to 100%. This significant advantage is attributed 1) the capacity of transfer learning to utilize prior knowledge from related domains, even in data-scarce target tasks, and 2) the proficiency of MFCC in capturing and representing the rich and essential information embedded within cough sounds. Furthermore, we propose an Android-based smartphone application that serves as a noninvasive and real-time prescreening tool. Our system holds significant importance to complement medical efforts containing respiratory diseases and pandemics in infected areas, making it applicable to any respiratory condition or pandemic where cough is a predominant symptom.

Sixth-generation (6G) networks anticipate intelligently supporting a wide range of smart services and innovative applications. Such a context urges a heavy usage of Machine Learning (ML) techniques, particularly Deep Learning (DL), to foster innovation and ease the deployment of intelligent network functions/operations, which are able to fulfill the various requirements of the envisioned 6G services. The revolution of 6G networks is driven by massive data availability, moving from centralized and big data towards small and distributed data. This trend has motivated the adoption of distributed and collaborative ML/DL techniques. Specifically, collaborative ML/DL consists of deploying a set of distributed agents that collaboratively train learning models without sharing their data, thus improving data privacy and reducing the time/communication overhead. This work provides a comprehensive study on how collaborative learning can be effectively deployed over 6G wireless networks. In particular, our study focuses on Split Federated Learning (SFL), a technique that recently emerged promising better performance compared with existing collaborative learning approaches. We first provide an overview of three emerging collaborative learning paradigms, including federated learning, split learning, and split federated learning, as well as of 6G networks along with their main vision and timeline of key developments. We then highlight the need for split federated learning towards the upcoming 6G networks in every aspect, including 6G technologies (e.g., intelligent physical layer, intelligent edge computing, zero-touch network management, intelligent resource management) and 6G use cases (e.g., smart grid 2.0, Industry 5.0, connected and autonomous systems). Furthermore, we review existing datasets along with frameworks that can help in implementing SFL for 6G networks. We finally identify key technical challenges, open issues, and future research directions related to SFL-enabled 6G networks.

Training without sharing data is one of the drivers that makes Federated Learning (FL) more attractive, compared to centralized approaches. However, requiring each learner to train the full model may not be efficient, particularly for devices with restricted resources, such as those available in Unmanned Aerial Vehicles (UAVs). To address this issue, a variation of FL technique, specifically Split Federated Learning (SFL), has recently been proposed. Unlike FL, the key concept of SFL is to divide the layers of the neural network among the involved learners. Therefore, each individual client will train only a segment of the model (submodel) rather than the entire model. Clearly, this technique, besides data privacy, optimizes the utilization of computational resources, reduces client-side training time, and enhances model privacy. However, there are questions that require answers: How should we split the model? Shall we systematically divide it in half, or is there a more optimal approach? In this line of thought, this paper provides a detailed analysis of possible splitting schemes of a power consumption prediction model for UAV s. First, the SFL-enabled model is presented. Second, an experimental analysis is conducted in which different splitting alternatives are made and numerically analyzed to examine the influence of network layering on split federated learning performance.

With the growing presence of artificial intelligence (AI) technologies, smart agriculture has seen significant advances in recent years. The deployment of smart sensors, drones, and robotics integrated with AI algorithms in agricultural settings enables the acquisition and assessment of extensive agricultural data, including soil and crop health information, weather conditions, and pest infestation levels. This technological integration assists farmers in automating mundane agricultural activities, enhancing productivity, and implementing targeted interventions. Date farming is a large industry in Algeria that requires effective preservation strategies. Unfortunately, the cultivation of date palms is constantly threatened by numerous diseases and pests, resulting in substantial decreases in crop yield. Therefore, timely detection of insect infestations is crucial. In this context, our work focuses primarily on detecting and classifying the insects that attack date palm fruits. To achieve this, we employ transfer learning and object detection techniques. The developed model consistently demonstrates high performance in terms of accuracy, precision, and recall, indicating its reliability for real-world applications. It can detect harmful insects before they infect date palms. This early detection capability can greatly contribute to the implementation of timely intervention and preventive measures, effectively reducing crop losses.

Transport services issues are one of the motivating reasons that push research and engineering communities to design and build smart cities. The fifth generation of mobile communications (5G) and Intelligent Transportation Systems (ITS) play a major role to improve transportation efficiency. Two kinds of messages are basically transmitted in 5G-enabled ITS - event-driven and periodic messages. The former are sent whenever a road hazard event like traffic accidents is detected, whereas the latter are generated by each vehicle to advise neighbors about its status information like position, speed, and direction. A high transmission rate of periodic messages consumes a large amount of bandwidth and causes a channel congestion, as well as, a low transmission rate could alter the neighbors discovery process. In this work, a simple and efficient self-adaptive beacons transmission scheme based on autonomic computing is proposed. The purpose is to reduce the overhead in the network and give more chance to higher priority traffic (like immediate emergency message) to access to the radio channel without distorting the view of node's local topology. The solution is validated with a safety message broadcasting protocol. The simulation results show that the proposed mechanism improves the protocol's performance.

We propose a reliable dissemination protocol for broadcasting safety messages in vehicular ad hoc networks called Segment Delay Based Broadcasting Protocol (SDBP). The protocol has a twofold goal: limiting the risk of interference and reducing the dissemination time. To achieve these goals, two mechanisms are proposed. The first one divides vehicle's coverage area into several segments depending on the local density. Thereafter, the priority to relay a message is given to nodes that are in the farthest segment from the source node. The second mechanism allows reducing the waiting time thanks to a periodic update process. The performances of SDBP have been studied in an environment with multiple concurrent data traffics. The goal was to validate its capacity when the radio channel becomes overloaded. The comparison study (in terms of delivery ratio, dissemination time, forwarders and redundancy packets ratio) shows that SDBP outperforms two VANETs' broadcasting protocols.

A Vehicular Ad hoc Network (VANET) is an interconnection of vehicles that communicate through wireless technologies. It offers to road users a wide variety of applications which can be classified into four main categories: safety, road traffic, comfort and infotainment. This paper deals with safety applications. Their main goal is to detect critical road conditions (e.g. accidents, black ice, etc.) and/or send notifications to other vehicles in the network. An effective dissemination of such a message relies on multi-hop retransmissions. Thus an explicit or implicit cooperation between vehicles is needed in order to relay the message over a wide area. The main challenge is to avoid the broadcast storm problem. This paper proposes an efficient segment-delay based method that divides the road into several segments depending on the network density and utilises a waiting time update technique to expedite the dissemination process with respect to network performance.

Bringing to the market intelligent vehicles is one of the current challenges faced by car manufacturers. These vehicles must be able to communicate in order to cooperate and be more effective. The issue of inter-vehicle communications is an active research topic. This paper proposes a reliable geographical broadcasting protocol which has a twofold goal: limiting the risk of interference and reducing the dissemination time. To achieve theses goals, two mechanisms are proposed. The first one divides the road (more precisely, each vehicle's coverage area) into several segments depending on the local density. Thereafter, the priority to relay a message is given to nodes that are in the farthest segment from the source node. The second mechanism allows to reduce the waiting time thanks to a periodic update process. This paper also analysis the performance of geographical broadcasting protocols in case of multiple simultaneous communications. The goal is to observe how these protocols behave when the radio channel becomes overloaded. The comparison study (in terms of packet loss and dissemination time) shows that the proposed protocol outperforms two other VANETs' broadcasting protocols.

Many studies demonstrated that Mobile Ad hoc networks routing protocols are not suitable for Vehicular ad hoc networks; the main reason relies on high mobility that causes a rapid topology change that leads to partitioning and routing link failure issues. Adaptable existing schemes also demonstrated a poor network performance, especially when the network density increases. The alternative is to develop new efficient routing schemes for VANETs. Trajectory based routing where the packet is forwarded from the source to the destination based only on vehicle's trajectory information constitutes one class of forwarding protocols that are proposed for VANETs. This paper surveys such class of protocols, with a particular interest on their main features that have made them efficient for VANETs, and their comparison with respect to some standards metrics. Future directions with respect to VANETs routing schemes are also discussed.