Vehicular Ad-Hoc Networks (VANETs) are essential for enhancing traffic management and road safety through vehicle-to-vehicle (V2V) and vehicle-to-infrastructure (V2I) communication. Accurately predicting vehicle trajectories is critical yet challenging in dynamic traffic conditions. The paper proposes an optimized hybrid deep learning model combining Convolutional Neural Networks (CNNs) and Long Short-Term Memory (LSTM) networks to improve trajectory prediction. Simulation results on real-world datasets (GPS tracks of vehicles on highways and in urban areas) demonstrate higher prediction accuracy and efficiency, making the model highly effective for deployment in real-time smart city systems.

Improving urban mobility management has become increasingly challenging due to the rapid growth in both population and vehicular traffic, impacting the fluidity of mobility and leading to traffic congestion, delays, economic burdens, and adverse effects on public health. Moreover, there are significant concerns regarding air pollution, road accidents, and greenhouse gas emissions associated with this trend. Addressing these issues requires comprehensive strategies that prioritize sustainable transportation modes and urban planning to enhance efficiency and mitigate the negative impacts of mobility on the environment and public well-being. To address these challenges, cities must develop innovative strategies that integrate predictive models into their urban mobility planning. This paper presents a novel approach to predicting trajectories in Vehicular Ad hoc Networks (VANETs). Our proposed architecture leverages recurrent neural networks (RNNs) particularly long short-term memory (LSTM) to capture essential spatial features and temporal dependencies inherent in historical trajectories. Numerical results show that the proposed solution is efficient in terms of prediction.

Smart Car Parks (SCPs) based on Wireless Sensor Networks (WSNs) are one of the most interesting Internet of Things applications. This paper addresses the deployment optimization problem of two-tiered WSNs dedicated to fire monitoring in SCPs. Networks deployed inside the SCP consist of three types of nodes: Sensor Nodes (SNs) which cover the spots within the parking area, Relay Nodes (RNs) which forward alert messages generated by SNs, and the Sink node which is connected to the outside world (e.g, firefighters), through a high bandwidth connection. We propose an algorithm based on chaos theory and Whale Optimization Algorithm (WOA), which minimizes simultaneously the deployed number of SNs, RNs, and network diameter while ensuring coverage and connectivity. To evaluate the effectiveness of our proposal, we have conducted extensive tests. The results show that the Chaos WOA (CWOA) outperforms the original WOA in terms of solution quality and computation time and by comparison with an exact method, CWOA provides results very close to the optimal in terms of fitness value and is efficient in terms of computational time when the problem becomes more complex.

The exponential growth of the Internet-of-Things (IoT) technology paradigm has resulted in new applications and on-line services. Smart car park is one interesting example among others that can take advantage of applications based on wireless sensor networks (WSNs) Which constitute the core of IoT. This paper focuses on the deployment optimization problem of WSNs dedicated to the fire detection in a smart car park. In such networks, the nodes are classified into two categories: Sensor Nodes (SNs) deployed within the smart car park for targets coverage and Relay Nodes (RNs) whose task is to relay alert messages generated by the sensor nodes up to the sink node. In this study, we propose a Multi-Objective Binary Integer Linear Programming (MOBILP) which minimizes simultaneously the number of sensor nodes, relay nodes and the maximum distance from sensor nodes to the sink node, while ensuring coverage and connectivity. We have conducted extensive tests in order to evaluate the performance of our proposal. The results demonstrate that the MOBILP outperforms the existing approaches in terms of quality of solutions compared to a sequential deployment method, which consists to deploy SNs then RNs, and in terms of the ability to find other efficient solutions compared to a simultaneous deployment method using a mono-objective function, which consists to deploy SNs and RNs simultaneously.