Unmanned Aerial Vehicles (UAVs) are increasingly deployed in large-scale Wireless Sensor Networks (WSNs) for applications ranging from extending coverage to environmental monitoring and disaster response. Many machine learning techniques, particularly Reinforcement Learning (RL), have been employed to support efficient multi-UAV operations. However, existing approaches still struggle with effective coordination among multiple UAVs, and often rely on static, manually tuned reward functions that lack adaptability for dynamic environmental changes. Our paper presents a novel decentralized approach for multi-UAV sensor coverage that combines explainable reward shaping with Double Deep Q-Network (Double-DQN) reinforcement learning. We first adopt Double-DQN to allow each UAV to independently learn and act based on local observations while coordinating to maximize area coverage, conserve energy, minimize latency, and avoid collisions. We leverage SHapley Additive exPlanations (SHAP) to assess the impact of individual input features on UAV decisions, providing transparent insights into the rationale behind agent actions. We then propose a SHAP-based adaptive reward weighting mechanism that adjusts reward priorities dynamically based on feature importance. Extensive simulations, conducted under varied system parameters reflecting real-world conditions, demonstrate that our approach significantly improves coverage efficiency, energy utilization and collision avoidance, highlighting the promise of integrating explainability and adaptivity in real-time multi-agent UAV systems.

The delivery of emergency supplies in disaster-stricken areas is often hindered by damaged infrastructure and inaccessible roads. Unmanned Aerial Vehicles (UAVs) provide a promising alternative due to their agility and rapid deployment. While prior works have explored AI-driven UAV routing and path planning, they often lack real-time inter-UAV coordination, dynamic task reassignment, and integrated decision-making under failure or resource constraints. This work proposes a comprehensive framework that integrates hazard-aware planning, intelligent task allocation, dynamic mission eligibility verification, UAV routing and coordination. First, we generate spatial hazard maps from aerial imagery to identify high-risk zones and target locations. We then propose a dynamic task allocation algorithm to determine the optimal number of UAVs and assigning targets based on UAV capabilities and environmental constraints. To support learning and decision-making, we develop a simulation environment that replicates diverse disaster scenarios and produces a labeled dataset capturing mission success under varying system parameters. We then leverage Deep Reinforcement Learning to provide real-time path planning, inter-UAV collaboration and mission adaptation for relief supply delivery in complex disaster environments. Our proposed Deep Q-Network (DQN) integrates weather forecasts, UAV sensor data, battery levels, and hazard information to output discrete UAV actions, including navigation, payload delivery, and backup requests from nearby UAVs. By combining hazard-aware mapping, intelligent task allocation, simulation-driven learning, and DQN-based control, our proposed framework enables adaptive UAV deployment, intelligent route planning, and collaborative multi-UAV behavior, ultimately improving mission reliability, safety, and delivery performance in emergency relief operations.

The growth of the Internet of Things (IoT) has triggered a technological revolution leading to significant advancements in various fields and industries, especially with the ability to connect and collect data from a wide range of devices and sensors. The collection of relevant and important data with high Value of Information (VoI) from sensor nodes (SNs), generally located in difficult-to-reach limited access areas, can allow the systems to learn from their environment, adapt, and improve the decision-making process. In our work, we consider VoI-aware energy-efficient data collection from sensor nodes using Unmanned Aerial Vehicles (UAVs). We formulate the joint UAV deployment and SN-to-UAV association problems as an optimization problem, aiming at deploying the minimum number of UAVs to collect the maximum amount of data with a maximum value of information while minimizing energy consumption, subject to latency and coverage constraints. We then propose using Genetic Algorithms (GAs) to provide real-time sub-optimal solutions while ensuring the tradeoff between different objectives. Simulations were conducted to show the performance and effectiveness of the proposed approach under different system parameters.

Disaster management plays a pivotal role in mitigating risks and ensuring effective response to crises. Integrating Federated Learning (FL) becomes essential to enable decentralized learning while preserving data privacy and protecting sensitive information during real-time decision-making crisis scenarios. While FL offers significant advantages, it is susceptible to various security threats, such as poisoning and data inference attacks. Therefore, strong security protocols along with FL client selection are needed to ensure efficient model training and high system reliability, particularly since clients vary in data quality, computational power, and network stability. In this paper, we propose a context-aware security (CAS) framework for FL in heterogeneous IoT settings for disasters identification and classification. The proposed framework dynamically adapts the security protocol chosen and selects the best clients for training by continuously monitoring and evaluating the system’s context, which includes factors such as device computational ability, energy level, data quality, and communication channel reliability. Simulations are then conducted on image data demonstrating our framework’s effectiveness in enhancing the overall accuracy while reducing computational overhead and energy consumption and maintaining security in dynamic IoT environments.

Integrating device-to-device (D2D) cooperation with mobile edge computing (MEC) for computation offloading has proven to be an effective method for extending the system capabilities of low-end devices to run complex applications. This can be realized through efficient computing data offloading and yet enhanced while simultaneously using multiple wireless interfaces for D2D, MEC and cloud offloading. In this work, we propose user-centric real-time computation task offloading and resource allocation strategies aiming at minimizing energy consumption and monetary cost while maximizing the number of completed tasks. We develop dynamic partial offloading solutions using the Lyapunov drift-plus-penalty optimization approach. Moreover, we propose a task admission solution based on support vector machines (SVM) to assess the potential of a task to be completed within its deadline, and accordingly, decide whether to drop from or add it to the user’s queue for processing. Results demonstrate high performance gains of the proposed solution that employs SVM-based task admission and Lyapunov-based computation offloading strategies. Significant increase in number of completed tasks, energy savings, and cost reductions are resulted as compared to alternative baseline approaches.

The curricular structure and the complexity of the prerequisite dependencies in a curriculum are essential factors that impact student progression, and ultimately graduation rates. However, we are not aware of any closed-form methods for quantifying the relationship between the complexity of a curriculum and the graduation rate of those attempting to complete the curriculum. This paper introduces a new method that quantifies this relationship using Markov Decision Processes (MDP). The non-deterministic nature of student progress along with their evolving states at each semester make MDP a suitable framework for this work. We propose a novel model that is useful due to the fact that it provides a closed-form solution approach that can be utilized to perform “what-if” analyses around student progress through a curriculum. The results confirm the inverse relationship between the complexity of a curriculum and the graduation rate of those students attempting to complete it. This is validated using a Monte Carlo simulation method. The results also provide useful insights that may guide future work in this area.

The vision towards 5G and beyond is to provide remarkable performance enhancements that enable the launch of new services and markets in different industry verticals. Example scenarios of those services include indoor hotspot, broadband access in a crowd, and dense urban; many of which require very high data rates. Traffic offloading and device-to-device cooperation have been leveraged to expand the system capacity and coverage through using heterogeneous network technologies. In this work, we shed the light on the significant gains incurred when predicted short term network performance is factored into network splitting decisions over multiple wireless interfaces, while guaranteeing a desired quality of experience to end users. Accordingly, we allow dynamic use of multiple network interfaces taking into consideration their energy requirement and price models to deliver premium services and minimize the overall energy consumption and total cost. We develop a novel and efficient real-time traffic splitting approach that makes use of predicted bit rate of each network interface in addition to device-to-device cooperation to decide on the amount of video traffic to be delivered on each interface at every time slot. The proposed approach is validated and evaluated under realistic network conditions. Simulation results demonstrate substantial gains in terms of energy consumption, data cost and quality of user experience as compared to multiple alternative solutions.

Ultra dense networks and device-to-device communications are expected to play a major role in 5G networks to meet tremendous traffic requirements. In our work, we address traffic offloading in dense device-to-device cooperative heterogeneous networks with focus on use cases where a very large number of users request simultaneously common streaming content from a remote server with quality of service guarantees. We formulate an optimization problem to maximize the number of users served and reduce the number of access points deployed while satisfying a set of system constraints. The solution determines the best strategy for downloading the content either over long range connectivity from the access points or short range connectivity from peer mobile devices. Results are presented for various scenarios in a stadium setting to demonstrate the significant gains of optimized traffic offloading in ultra dense wireless networks.

To meet the huge traffic growth, heterogeneous networks composed of wireless local area networks (WLAN) and cellular networks are used to provide higher capacity and coverage. When the two networks are available, switching from one network to the other when downloading data is needed to provide good system performance. This paper proposes a fuzzy logic based approach for an automated network selection based on real-network implementations and measurements. The proposed network selection model is based on fuzzy inference rules considering features that affect the selection decision and are available to the user's device. The model input features are linguistic variables representing the signal strength reflecting the channel quality of WiFi and 3G links and network load. Using fuzzy inference rules, WiFi and cellular data rates are inferred from the fuzzy sets of the input variables. Then, the final network selection decision is either WiFi or cellular link based on the fuzzified WiFi and 3G rates and corresponding if-then inference rules. In addition, the performance of the proposed fuzzy logic approach for real-time network selection is evaluated and shown superior to the use of WiFi and 3G links separately.

Heterogeneous networks are expected to play a major role towards meeting the exploding traffic demand over cellular systems. Particularly, existing WiFi hotspots will be dynamically utilized to offload the traffic of cellular mobile subscribers. This will be further facilitated by forthcoming advances in mobile device capabilities that will include the ability to operate multiple wireless interfaces simultaneously. To this end, we focus in this work on cellular/WiFi heterogeneous networks with traffic splitting where a mobile device can utilize existing cellular and WiFi links simultaneously to achieve various performance gains. We propose a multi-objective approach for traffic splitting that captures the tradeoffs between throughput maximization on one hand and battery energy minimization on the other hand. We evaluate the proposed approach using parameters determined via experimental measurements using Samsung Galaxy SIII mobile devices. Results are presented for various scenarios in order to quantify and analyze the throughput-energy tradeoffs of traffic splitting in cellular/WiFi heterogeneous networks.

The most challenging issue in WiMAX network planning is to measure and enhance the Quality of Service (QoS) of WiMAX networks. In this paper, a comprehensive WiMAX simulator is proposed to evaluate the performance of the system. The key parts of the simulator are described including end-to-end communication path, traffic generation, Medium Access Control (MAC) and Physical (PHY) layers, resource allocation, frame construction and configuration options such as Adaptive Modulation and Coding (AMC). Several experiments are conducted to assess different scenarios while varying one or more of the following: input traffic size, traffic load, presence of fragmentation and AMC. The results show the scalability of the system as it can support a large number of users while showing the real-life representation of the traffic models. The simulations also show the flexibility of implementing AMC schemes according to desired distributions. The high accuracy of the simulator is shown by comparing the simulator results to theoretical expected values.

Minimizing energy consumption is an urgent and challenging problem. As in any communication system, high energy efficiency in WiMAX systems should be maintained by increasing resource efficiency. Thus, WiMAX resources should be properly utilized by optimizing the construction of downlink (DL) bursts. This paper proposes an energy-efficient scheme that maximizes the use of resources at the base station (BS) by reducing the energy wasted caused by sending padding bits instead of useful data. The problem was formulated as nonlinear integer programming model. Due to the complexity of the problem, this paper presents first the formulation of the base model for optimal DL bursts construction problem assuming the packet is represented by one burst. Then, the formulation is expanded to allow the representation of packets by several bursts. The results show an improvement in data packing that maximizes the utilization of frames, and minimizes energy wastage.