Unmanned aerial vehicles (UAVs) have recently been applied in several contexts due to their flexibility, mobility, and fast deployment. One of the essential aspects of multi-UAV systems is path planning, which autonomously determines paths for drones from starting points to destination points. However, UAVs face many obstacles in their routes, potentially causing loss or damage. Several heuristic approaches have been investigated to address collision avoidance. These approaches are generally applied in static environments where the environment is known in advance and paths are generated offline, making them unsuitable for unknown or dynamic environments. Additionally, limited flight times due to battery constraints pose another challenge in multi-UAV path planning. Reinforcement learning (RL) emerges as a promising candidate to generate collision-free paths for drones in dynamic environments due to its adaptability and generalization capabilities. In this study, we propose a framework to provide a novel solution for multi-UAV path planning in a 3D dynamic environment. The improved particle swarm optimization with reinforcement learning (IPSO-RL) framework is designed to tackle the multi-UAV path planning problem in a fully distributed and reactive manner. The framework integrates IPSO with deep RL to provide the drone with additional feedback and guidance to operate more sustainably. This integration incorporates a unique reward system that can adapt to various environments. Simulations demonstrate the effectiveness of the IPSO-RL approach, showing superior results in terms of collision avoidance, path length, and energy efficiency compared to other benchmarks. The results also illustrate that the proposed IPSO-RL framework can acquire a feasible and effective route successfully with minimum energy consumption in complicated environments.

Maximizing wireless sensor networks (WSNs) lifetime is a primary objective in the design of these networks. Intelligent energy management models can assist designers to achieve this objective. These models aim to reduce the number of selected sensors to report environmental measurements and, hence, achieve higher energy efficiency while maintaining the desired level of accuracy in the reported measurement. In this paper, we present a comparative study of three intelligent models based on Naive Bayes, Multilayer Perceptrons (MLP), and Support Vector Machine (SVM) classifiers. Simulation results show that Linear-SVM selects sensors that produce higher energy efficiency compared to those selected by MLP and Naive Bayes for the same WSNs Lifetime Extension Factor.

With the rapid growth of internet usage and the increasing number of connected devices, there is a critical need for advanced Network Traffic Classification (NTC) solutions to ensure optimal performance and robust security. Traditional NTC methods, such as port-based analysis and deep packet inspection, struggle to cope with modern network complexities, particularly dynamic port allocation and encrypted traffic. Recently, Convolutional Neural Networks (CNN) and Recurrent Neural Networks (RNN) have been employed to develop classification models to accomplish this task. Existing models for NTC often require significant computational resources due to their large number of parameters, leading to slower inference times and higher memory consumption. To overcome these limitations, we introduce a lightweight NTC model based on Depthwise Separable Convolutions and compare its performance against CNN, RNN, and state-of-the-art models. In terms of computational efficiency, our proposed lightweight CNN exhibits a markedly reduced computational footprint. It utilizes only 30,611 parameters and 0.627 MFLOPS, achieving inference times of 1.49 seconds on the CPU and 0.43 seconds on the GPU. This corresponds to roughly 4× fewer FLOPS than the RNN baseline and 16× fewer than the CNN baseline, while also offering an ultracompact design compared to state-of-the-art models. Such efficiency makes it exceptionally well-suited for real-time applications in resource-constrained environments. In addition, we have integrated eXplainable Artificial Intelligence techniques, specifically LIME and SHAP, to provide valuable insights into model predictions. LIME and SHAP help interpret the contribution of each feature in decision-making, enhancing the transparency and trust in the model's predictions, without compromising its lightweight nature. To support reproducibility and foster collaborative development, all associated code and resources have been made publicly available.

The rapid expansion of IoT devices has introduced significant security challenges, with malware authors constantly evolving their techniques to exploit vulnerabilities in IoT networks. Despite this growing threat, progress in developing effective detection solutions remains limited. In this study, we present an ML-based framework for detecting and classifying network threats targeting IoT environments. Using the CTU-IoT-Malware-Capture 2023 dataset and the UNSW Bot-IoT dataset, we transformed the task into a structured multi-class classification problem to better reflect real-world detection challenges. Our primary contribution lies in demonstrating the effectiveness of post-training quantization on gradient-boosted models, specifically a Quantized XGB variant enhanced with histogram-based quantization. This approach significantly reduces model size and inference time without sacrificing accuracy. The proposed model achieved high classification accuracies of 99.93% and 99.99% on the two datasets, while the quantization step led to 1.42× and 3× improvements in inference speed, and reductions in model size by 3.61× and 2.71×, respectively, making it well-suited for deployment in resource-constrained IoT settings. This work demonstrates not only the effectiveness of gradient boosting in handling complex traffic data but also introduces an efficient optimization strategy for real-time IoT threat detection.