An in-vehicle network (IVN) is the internal communication network that connects all sensors and control units in an autonomous vehicle. Sensors and control units use the IVN to send perception-related messages and control commands for the normal and safe operation of the vehicle. However, the IVN, by design, is vulnerable to network attacks due to a lack of adequate security mechanisms. This paper presents a Dynamic Windowing Intrusion Detection System (DWIDS) that adapts its detection window in real-time based on observed anomalies, enabling accurate and responsive attack detection. Unlike prior methods that focus on static configurations or single-attack detection, DWIDS supports multi-label classification and real-time tuning of detection parameters. The system is evaluated using two public benchmark datasets (CHD and IVN-IDS challenge) which feature diverse and imbalanced attack types. Experimental results demonstrate high performance across key metrics (e.g., >98% precision, >97% recall and F1-score), including for rare attacks. The findings confirm DWIDS’s practicality and robustness for deployment in real-world autonomous vehicle environments.

Recent advancements have sparked a growing interest in integrating spatiotemporal analysis with large-scale language models. However, spatiotemporal data often contains sensitive information, making it unsuitable for open third-party access. To address this challenge, we propose a Graph-GAN-based model for generating privacy-protected spatiotemporal data. Our approach incorporates spatial and temporal attention blocks in the discriminator and a spatiotemporal deconvolution structure in the generator. These enhancements enable efficient training under Gaussian noise to achieve differential privacy. Extensive experiments conducted on three real-world spatiotemporal datasets validate the efficacy of our model. Our method provides a privacy guarantee while maintaining the data utility. The prediction model trained on our generated data maintains a competitive performance compared to the model trained on the original data.

Video surveillance using drones is both convenient and efficient due to the ease of deployment and unobstructed movement of drones in many scenarios. An interesting application of drone-based video surveillance is to estimate crowd density (both pedestrians and vehicles) in public places. Deep learning using convolution neural networks (CNNs) is employed for automatic crowd counting and density estimation using images and videos. However, the performance and accuracy of such models typically depends upon the model architecture i.e., deeper CNN models improve accuracy at the cost of increased inference time. In this paper, we propose a novel crowd density estimation model for drones (DroneNet) using Self-organized Operational Neural Networks (Self-ONN). Self-ONN provides efficient learning capabilities with lower computational complexity as compared to CNN-based models. We tested our algorithm on two drone-view public datasets. Our evaluation shows that the proposed DroneNet shows superior performance on an equivalent CNN-based model.

Many real-world ubiquitous applications, such as parking recommendations and air pollution monitoring, benefit significantly from accurate long-term spatio-temporal forecasting (LSTF). LSTF makes use of long-term dependency structure between the spatial and temporal domains, as well as the contextual information. Recent studies have revealed the potential of multi-graph neural networks (MGNNs) to improve prediction performance. However, existing MGNN methods do not work well when applied to LSTF due to several issues: the low level of generality, insufficient use of contextual information, and the imbalanced graph fusion approach. To address these issues, we construct new graph models to represent the contextual information of each node and exploit the long-term spatio-temporal data dependency structure. To aggregate the information across multiple graphs, we propose a new dynamic multi-graph fusion module to characterize the correlations of nodes within a graph and the nodes across graphs via the spatial attention and graph attention mechanisms. Furthermore, we introduce a trainable weight tensor to indicate the importance of each node in different graphs. Extensive experiments on two large-scale datasets demonstrate that our proposed approaches significantly improve the performance of existing graph neural network models in LSTF prediction tasks.

This contribution presents a solution to improve the performances of micro unmanned aerial vehicles (UAVs) by increasing their missions coverage in terms of distance and time. This is achieved by letting the UAV ride existing land public transport such as the city bus throughout the route to its mission location. Indeed, due to their limited battery capacity, micro-UAVs flying time is restrained, which affects their mission and coverage performances. In this paper, we propose to leverage the use of public transport infrastructure, such as city buses, to carry the UAVs whenever it is possible in order to minimize their flight energy consumption. For this purpose, a generic scheduling framework to efficiently cover spatially and temporally distributed events in a geographical area of interest over a long period of time is proposed. By considering the public transport schedule table, a mixed integer linear programming problem (MILP) aiming at minimizing the total energy consumption of the UAVs is formulated while accomplishing all the pre-scheduled missions. The proposed proactive UAV scheduling framework optimizes the UAV trips according to the mission occurrence and the schedule table of the buses. The obtained results demonstrate the effectiveness of the collaboration between the UAVs and the land transport to improve the overall UAV missions' performances in terms of distance coverage.

The use of micro unmanned aerial vehicles (UAVs) have gained a lot of interests especially for smart city applications due to their three- dimensional (3D) mobility and flexibility. Path planning is one of the most important UAV problems that needs to be addressed. In this paper, we focus on determining the optimal routes for a fleet of UAVs in urban cities that minimize the total arrival time of all UAV swarms while respecting their energy consumption constraints and avoiding the risk of collision. Through a mixed integer linear program, we develop a safe navigation framework for realistic 3D maps where charging stations are made available to recharge UAV batteries on their ways to destination. Our results investigate different scenarios for selected system parameters and illustrate different collision avoidance techniques followed by the UAVs.

Most of the drone-based applications require a time-limited access to the spectrum to complete data transmission due to limited battery capacity of these flying units. This paper proposes an efficient spectrum and energy management solution by integrating the overlay cognitive radio technology. Therefore, we aim to use the drone as a secondary node and target to determine an optimized three-dimensional location and a resource control solution by which it can complete its data transfer and in parallel support the primary communication. To this end, a non-convex optimization problem is developed. The obtained solution minimizes the total energy consumption of the drone and, at the same time, maintains the required data rate level of the spectrum's owner. A resource allocation procedure and swarm intelligence-based positioning algorithm are jointly designed for this purpose. Numerical results show the efficiency of the proposed approach in terms of energy consumption savings and additional transmission opportunities as compared to other schemes.

In this paper, a generic scheduling framework to manage a fleet of micro unmanned aerial vehicles (UAVs) is proposed. The objective is to employ multiple UAVs in sequential and parallel ways to cover spatially and temporally distributed events in a geographical area of interest over a long period of time. The proactive scheduling framework considers several constraints and challenges including the limited battery capacities and technical specifications of the UAVs in addition to the necessity to regularly send back the UAVs to a docking station. A mixed integer linear programming (MILP) problem aiming at minimizing the total energy consumption is formulated after a series of linearization steps. Optimal UAV scheduling solutions are then obtained using off-the-shelf software. The proposed UAV scheduling framework is formulated in a generic manner and can be applied in multiple domains comprising short and/or long-term UAV missions while ensuring uninterrupted service. The obtained results can be used as convenient benchmarks for future heuristic UAV scheduling approaches.

This paper proposes an energy-efficient solution to employ a drone to gather data from spatially distributed wireless sensors. Specifically, we minimize the energy consumption of the drone while accomplishing a tour to collect the needed data. This tour accounts for both the energies due to data transfer and to the motion of the drone. The objective is to determine the positions where the drone stops to collect data from each cluster of sensors as well as the path that the drone needs to follow to complete its data gathering tour. The problem is decomposed into two sub-problems. The first sub-problem targets to determine the sub-groups of sensors and stop positions to collect data from each sub- group using a clustering approach. In the second sub- problem, we employ the travel salesman solution to find the path among these stops Selected numerical results show that the achieved energy is considerably reduced compared to the one of traditional approaches. Moreover, we study the behavior of the drone versus various system parameters.

This paper investigates the problem of data routing in flying ad hoc networks (FANETs) composed of multiple flying nodes, i.e., unmanned aerial vehicles (UAVs), supported by communication platforms. The objective is to exploit the mobility of UAVs in order to establish routing paths and transfer a message between two ground nodes at minimum transmission time. Assuming that the UAVs are already deployed to execute a given primary task, the cooperation of the UAVs in the data transfer process, considered as a secondary task, becomes subject to three conditions. First, the energy consumed by each UAV has to respect the allocated budget for the data routing process. Second, the UAVs cannot move out of the boundaries of a tolerated and well-defined region in order to maintain the operation of the primary task. Finally, the UAVs need to reduce their traveled distances in order to reduce the delay of the transfer. A mixed non-linear integer programming problem determining the routing path and the new locations of the UAVs participating in the data transfer process is formulated. Due to its nonconvexity, we proceed with a deterministic exploratory strategy inspired from the Hooke-Jeeves algorithm to meet the problem goals. Selected numerical results investigate the performance of the proposed solution for different scenarios and compare some of them to those of a metaheuristic approach based on swarm intelligence.

Unmanned Aerial Vehicles (UAV) have attracted a lot of attention in a variety of fields especially in intelligent transportation systems (ITS). They constitute an innovative mean to support existing technologies to control road traffic and monitor incidents. Due to their energy-limited capacity, UAVs are employed for temporary missions and, during idle periods, they are placed in stations where they can replenish their batteries. In this paper, the problem of UAV docking station placement for ITS is investigated. This constitutes the first step in managing UAV-assisted ITS. The objective is to determine the best locations for a given number of docking stations that the operator aims to install in a large geographical area. Based on average road network statistics, two essential conditions are imposed in making the placement decision: i) the UAV has to reach the incident location in a reasonable time, ii) there is no risk of UAV's battery failure during the mission. Two algorithms, namely a penalized weighted k-means algorithm and the particle swarm optimization algorithm, are proposed. Results show that both algorithms achieve close coverage efficiency in spite of their different conceptual constructions.

Wireless Sensor Networks have been used for many applications especially for sites monitoring and surveillance. This contribution proposes a new grid-based architecture to monitor an area of interest that could be of a large size through a number of energy efficient sensors deployed randomly to cover the whole area. The proposed solution relays on a grid-based scheme where the monitored area is logically divided into small rectangular cells and in each cell at least one sensor is deployed. The status of the sensors located within a certain cell tells the situation in that cell either in hazard state or not, as well as the situation of other cells around. When a hazard is detected, all the deployed sensors enter into a dynamic cooperation to ensure an energy-efficient dissemination of the whole area with an alert about the new hazard. The proposed solution has been validated through intensive simulations which show an important improvement in terms of overall network overhead as well as overall network energy consumption.

In Vehicular Ad-hoc Networks (VANETs), any vehicle uses a location service to get an up-to-date data of all vehicles' positions in its vicinity. Many location services rely on infrastructures to perform location update and location query tasks. However, the infrastructure penetration rate may differ from one region to another. We propose in this paper a new location service called Vehicle-Aided Location Service in urban environment (VALS) which resolves the problem of the shortage of infrastructure in some city districts. VALS replaces the missing Road-Side Units (RSU) with vehicles offering RSUs functionalities. It is based on a hierarchical and cluster-based design. Simulation results show that VALS achieves a high success ratio (86%), get most vehicles' data (82%) and a good position information level accuracy (less than 20 m) with a low RSU penetration rate (40%).

To gather and transmit data, low cost wireless devices are often deployed in open, unattended and possibly hostile environment, making them particularly vulnerable to physical attacks. Resilience is needed to mitigate such inherent vulnerabilities and risks related to security and reliability. In this paper, Routing Protocol for Low-Power and Lossy Networks (RPL) is studied in presence of packet dropping malicious compromised nodes. Random behavior and data replication have been introduced to RPL to enhance its resilience against such insider attacks. The classical RPL and its resilient variants have been analyzed through Cooja simulations and hardware emulation. Resilient techniques introduced to RPL have enhanced significantly the resilience against attacks providing route diversification to exploit the redundant topology created by wireless communications. In particular, the proposed resilient RPL exhibits better performance in terms of delivery ratio (up to 40%), fairness and connectivity while staying energy efficient.

The number of vehicles on roads keeps increasing continuously, making the management of traffic flow, especially in big cities more and more challenging. One of the key enablers for having smooth traffic flows and better mobility is to rely on real-time traffic monitoring systems. These systems allow road operators to implement intelligent traffic management strategies such as the dynamic adjustment of timing and phasing of traffic lights and the adaptive road congestion charging. Moreover, better informed travelers will plan smartly their journeys and hence potentially contribute in reducing traffic jams. Traditional real-time traffic monitoring usually get real-time data from GPS-equipped fleets and fixed sensors installed in specific locations. In this paper, a new real-time traffic monitoring based on emerging vehicular communication systems is proposed. The system enables traffic monitoring with higher reliability, accuracy, and granularity. The cluster-based V2X traffic data collection mechanism is able to gather more than 99% of the available data and reduce the overhead to one quarter when compared to other approaches.

This paper presents experimental results on a fully functional body area network (BAN) platform in terms of energy consumption, delivery ratio and lifespan. The proposed BAN platform captures, processes, and wirelessly transmits six-degrees-of-freedom inertial and electrocardiogram data in a wearable, non-invasive form factor. A dynamic TDMA MAC layer has been implemented over a 802.15.4 physical layer as well as 2 lightweight protocols: a similarity-based filter to reduce the number of packets sent by the sensors and a polynomial interpolation technique to reduce the size of the packets sent by the coordinator. The system is evaluated regarding the delivery rate, the energy consumption efficiency and the lifetime while considering 3 scenarios and several human activities (sitting, walking, and running). In addition, we compare the sensors' lifespan when bluetooth or 802.15.4 is used. The experimental results show that the proposed MAC layer reduces the number of collisions and is particularly adapted to periodic data traffic from biomedical sensors. Moreover, significant improvements in energy consumption and lifetime are observed enabling health care applications and remote monitoring in harsh environments.

This paper presents an analysis of link asymmetry in 5.9GHz vehicular communication by means of on-road experiments, and using a standard compliant vehicular communication platform. Similar works have been conducted in the last decades, especially by relevant industrial stakeholders, but none or only little information has been disclosed to the public. The link asymmetry may have considerable impact on the performance of the adopted communication protocols, therefore it is highly important to study such a topic and share the outcomes with the researcher community; this is one of the main motivations behind this contribution. The importance of the results is twofold: first we show that the antenna position on the car roof has a considerable impact on the communication link, and second we demonstrate that the link symmetry is not as worst as can be imagined since the experiments show that a link can still have a good symmetry up to 300 meters of distance between two connected vehicles.

This paper presents experimental results on the Routing Protocol for Low-Power and Lossy Networks (RPL). The RPL properties in terms of delivery ratio, control packet overhead, dynamics and robustness are studied. The results are obtained by several experimentations conducted on 2 large wireless sensor network testbeds composed of more than 100 sensor nodes each. In this real-life scenario (high density and convergecast traffic), several intrinsic characteristics of RPL are underlined: path length stability but reduced delivery ratio and important overhead. To investigate the RPL robustness, we observe its behavior when facing a sudden death of several sensors and when several sensors are redeployed. RPL shows good abilities to maintain the routing process despite such events. However, the paper highlights that this ability can be reduced if only few critical nodes fail. To the best of our knowledge, it is the first study of RPL on such large platform.

Vehicular communication is an important part of the Intelligent Transportation Systems (ITS). Geographic routing in vehicular ad hoc network (VANET) is becoming an interesting topic to deliver safety messages between cars but also between a car and a roadside infrastructure within a designated destination area. The Car2Car Communication Consortium specified C2CNet architecture as a geographic routing protocol. The results of GeoNet project are presented in the paper, which aims at combining IPv6 networking and C2CNet. The system with IPv6 and C2CNet is designed and implemented in Linux. The prototype implementation is first evaluated indoor testbed with the fixed positions. Then it is evaluated in the field testbed with three vehicles with various scenarios. For evaluation in field testbed, we have developed the AnaVANET evaluation tool to perform the evaluation taking into account all of geographic factors.

Nowadays, researchers show more and more interests to vehicular ad hoc networks (VANETs), which are a specific instance of mobile ad hoc networks (MANETs) where nodes are vehicles. In VANETs, vehicles have no energy resource constraint which could extend coverage and network lifetime, but have a high mobility patterns that cause frequent and fast topology changes. Consequently, VANETs have particular research interests, like dedicated MAC and routing optimization. In our previous work, we have proposed movement prediction-based routing (MOPR) concept for VANETs, which improves the routing process by selecting the most stable route in terms of lifetime with respect to the movement of vehicles. And in this paper, we present how this MOPR concept can be applied to position-based routing protocols, and how it improves their performances. Based on simulation results we compare MOPR with the position-based routing protocol GPSR and another movement-based routing protocol called MORA.