The use of smart fishing devices (SFDs) is expanding for applications in marine science and fisheries management. These devices signal a capture event through low-power wide-area networks (LPWAN) or non-terrestrial networks (NTN), providing real-time data. A critical challenge in these applications is ensuring the healthy release of non-target species, as post-release stress and survival are strongly species-specific. Consequently, identifying the species that has triggered the device is paramount. This study investigates whether the analysis of an SFD’s GPS periodic position is sufficient to infer the captured species. We examined a dataset comprising 11,905 GPS positions from 983 distinct capture events. Our findings indicate that GPS data is not sufficient for accurate species classification. However, the data can effectively be used to detect self-release events, achieving 72% accuracy from a sequence of 3 GPS positions and 80% accuracy from 12 positions. This finding demonstrates that SFD positional data is a promising tool for remotely monitoring gear availability. Furthermore, the inability to classify species with this data highlights the need to incorporate more granular sensors, such as accelerometers or higher-frequency GPS, in future work.

Vehicular networks have emerged in the past years as one of the most promising technologies in the context of Intelligent Transportation Systems. Several applications have recently been envisaged to improve the lives of citizens in different ways, particularly in the field of safety. In this work we focus on a different direction by leveraging on vehicular communication technologies and software-defined networking (SDN) to achieve a solution able to improve the travel time of emergency vehicles (EVs) when traveling in urban environments. In particular, we devise a solution where the route to be followed by EVs is shared with an SDN-enabled infrastructure, being then smartly rebroadcast using the roadside units (RSUs) that are near the region the EV will pass by in a near future. This way, standard vehicles that are ahead of the EV are notified about its coming, and clear the required lane to facilitate a faster and obstacle free path for the EV’s journey. Simulation experiments based on the SUMO traffic simulator for the city of Valencia, Spain, have shown that, if properly tuned, the proposed solution is able to reduce the travel time of EVs by nearly 15%, while maintaining the travel time of other vehicles mostly unaltered.

The Border Gateway Protocol (BGP) is in charge of the route exchange at the Internet scale. Anomalies in BGP can have several causes (misconfigurations, outages and attacks). Forged AS paths are small scale and subtle attacks on BGP and therefore are hard to detect. In this paper we use a Machine Learning (ML) model applying a Long Short-Term Memory (LSTM) based Recurrent Neural Network (RNN) architecture to take the temporal aspect of BGP into account. We show that our ML model is able to detect forged AS path anomalies with an accuracy of 67% and a precision of 72%. These preliminary results outperform the existing proposals and allow us to think that ML on temporal graphs is worth investigating.

The Border Gateway Protocol (BGP) builds the communication routes at the Internet scale. Anomalies in BGP have several causes and can impact the Internet stability. BGP data traces are complex and require specific methods such as machine learning to be processed for anomaly detection. Two types of features are used to study large scale events with machine learning models: graph features or statistical features. Despite the recent interest for the concept of Graph Neural Network (GNN), there is no proposal that adapts GNN for BGP anomaly detection directly from the BGP graph. In this paper, we propose BGNN, a GNN model which detects if a node is involved in a large scale BGP anomaly. Our results show a maximum accuracy of 96% and the model can detect an anomaly after 6 minutes with 90% accuracy. These results are promising and suggest GNN for BGP anomaly detection are worth investigating,

The Border Gateway Protocol (BGP) is in charge of the route exchange at the Internet scale. Anomalies in BGP can have several causes (mis-configuration, outage and attacks). These anomalies are classified into large or small scale anomalies. Machine learning models are used to analyze and detect anomalies from the complex data extracted from BGP behavior. Two types of data representation can be used inside the machine learning models: a graph representation of the network (graph features) or a statistical computation on the data (statistical features). In this paper, we evaluate and compare the accuracy of machine learning models using graph features and statistical features on both large and small scale BGP anomalies. We show that statistical features have better accuracy for large scale anomalies, and graph features increase the detection accuracy by 15% for small scale anomalies and are well suited for BGP small scale anomaly detection.

In this paper, we tackle the optimal energy replenishment problem (OERP) using a given number of flying drones, in order to efficiently recharge wireless sensor nodes. We present a linear program that maximizes the amount of harvested energy to the sensors. We show that the model is solved to optimality in a few seconds for sensor networks with up to 50 nodes. The small number of available drones is shown to be optimally deployed at low altitude in order to efficiently recharge the batteries of at least half of the sensor nodes.

In this paper we focus on the problem of dynamic event coverage. We assume that no knowledge about either event position or duration is given a priori. Nonetheless, the events need to be monitored and covered thanks to mobile wireless sensors. Thus, mobile sensors have to discover the events and move towards a new Zone of Interest (ZoI) when the previous monitored event is over. An efficient, distributed and localized solution of this problem would be immediately exploitable by several applications domains, such as environmental, civil, etc. We propose two novel approaches to deal with dynamic event coverage. The first one is a modified version of the PSO, where particles (mobile sensors, nodes or devices in the following) update their velocity by using only local information coming from their neighbors. In practice, the velocity update is performed by considering neighbors' sensed events. Our distributed version of PSO is integrated with a distributed version of the Virtual Force Algorithm (VFA). Virtual Force approach has the ability to “position” nodes with no overlap, by using attractive and repulsive forces based on the distance between nodes. The other proposed algorithm is a distributed implementation of the VFA by itself. Both techniques are able to reach high levels of coverage and show a satisfying reactivity when the ZoI changes. This output parameter is measured as the capability for the sensors to “follow” a sequence of events happening in different ZoIs. The effectiveness of our techniques is shown through a series of simulations and comparisons with the classical centralized VFA.

The coverage of Points of Interest (PoI) is a classical requirement in mobile wireless sensor applications. Optimizing the sensors self-deployment over a PoI while maintaining the connectivity between the sensors and the base station is thus a fundamental issue. This paper addresses the problem of autonomous deployment of mobile sensors that need to cover a predefined PoI with a connectivity constraint. In our algorithm, each sensor moves toward a PoI but has also to maintain the connectivity with a subset of its neighboring sensors that are part of the Relative Neighborhood Graph (RNG). The Relative Neighborhood Graph reduction is chosen so that global connectivity can be provided locally. Our deployment scheme minimizes the number of sensors used for connectivity thus increasing the number of monitoring sensors. Analytical results, simulation results and practical implementation are provided to show the efficiency of our algorithm.

Multihop wireless networks are used to provide internet connectivity to the users and the level of performance and quality expected by these users are increasing. In order to meet these performance and quality requirements, wireless communications should be enhanced. Previous works from the literature show that the performance and quality provided by an IEEE 802.11-based multihop wireless network are far from optimal and that there exist different ways to increase the efficiency and the quality of service of such a network. Some studies show that using the medium state as a parameter to tune the behaviour of an IEEE 802.11-based multihop network is an appropriate way to proceed. A station in a IEEE 802.11-based multihop wireless network senses the medium either busy or idle. The durations of idle periods and busy periods and their distributions have a clear impact on the network and nodes performance. The understanding of the relationship between these indicators, namely idle and busy periods, the network topology and the traffic, would give new insights to enhance the performance and quality of multihop wireless networks. Due to its multihop and distributed nature, the characterisation of idle period durations is difficult in such a network. This paper explores the characterisation of idle period distribution by proposing a new analytical model and provides an application of this characterisation with the design of an adaptive backoff algorithm based on idle periods.

Power consumption is an essential issue in wireless multimedia sensor networks (WMSNs) due to the elevated processing capabilities requested by the video acquisition hardware installed on the generic sensor node. Hence, node placement scheme in WMSNs greatly impacts the overall network lifetime. In this context, the paper first proposes a suitable hardware architecture to implement a feasible WMS node based on off-the-shelf technology, then it shows how the energy spaced placement of the wireless nodes reduces the energy consumption in comparison with the classical evenly spaced placement, without affecting the video quality of multimedia traffic.

Knowledge discovery and data analysis in resource constrained wireless sensor networks faces different challenges. One of the main challenges is to identify misbehaviors or anomalies with high accuracy while minimizing energy consumption in the network. In this paper, we extend a previous work of us and we present an algorithm for temporal anomalies detection in wireless sensor networks. Our experiments results show that our algorithm can efficiently and accurately detect anomalies in sensor measurements. It also produces low false alarm rate for slow variation time series measurements without harvesting the source of energy.

A primary purpose of sensing in a sensor network is to collect and aggregate information about a phenomenon of interest. The batteries on today's wireless sensor barely last a few days, and nodes typically expend a lot of energy in computation and wireless communication. Hence, the energy efficiency of the system is a major issue. Different representative mechanisms has been proposed to achieve a long lived sensors such as “clustering mechanisms” as well as Aggregation techniques to reduce the amount of data communication generated by sensors. Depending on the data type, ARMA series and forecasting are possible ways to reduce data transmission. In this work, we adopt single-hop clustering mechanism where all sensor nodes in a cluster communicate with their Cluster-Head (or sink) via single hop (such as In/On body sensors for personal health monitoring,..). We propose different data aggregation algorithms based on the AutoRegressive model, to predict local readings and reduce the communication traffic. We evaluate the performance of our work in terms of communication cost and energy consumption. We also extend our work to enhance the prediction accuracy by estimating dynamic prediction threshold. Our simulation shows that depending on data type, communication overhead and rate can be reduced and a considerable accuracy prediction can be obtained.

Some current and future pervasive data driven applications must operate in “extreme” environments where end-to-end connectivity cannot be guaranteed at all times. In fact, it is likely that in these environments partitions are, rather than exceptions, part of the normal network operation. In this paper, we introduce Cover, a suite of adaptive strategies to control the trajectory of “infrastructure” nodes, which are deployed to bridge network partitions and thus play a critical role in data delivery. In particular, we focus on applications where end (or target) nodes are mobile and their mobility is unknown. Our goal is then to deploy and manage infrastructure nodes so that application-level requirements such as reliable data delivery and latency are met while still limiting deployment cost and balancing the load among infrastructure nodes. Cover achieves these goals using a localized and adaptive approach to infrastructure management based on the observed mobility of target nodes. To this end, Cover takes advantage of contact opportunities between infrastructure nodes to exchange information about their covered zones, and thus, help monitor targets in a more efficient fashion. Through extensive simulations, we show how Cover's adaptive features yield a fair distribution of targets per infrastructure node based only on limited network knowledge.

Extending the lifetime of wireless sensor networks remains the most challenging and demanding requirement that impedes large-scale deployments. The basic operation in WSNs is the systematic gathering and transmission of sensed data to a base station for further processing. During data gathering, the amount of data can be large sometimes, due to redundant data combined from different sensing nodes in the neighborhood. Thus the data gathered need to be processed before being transmitted, in order to detect and remove redundancy, which can impact the communication traffic and energy consumption of the network in a negative way. In this paper, we propose an algorithm to measure similarity between the data collected toward the base station(relative to a specific event monitoring), so that an aggregator sensor sends a minimum amount of information to the base station in a way that the latter can deduce the source information of sensing neighbors nodes. Further, our experimental results demonstrate that the communication traffic and the number of bits transmitted can be minimized while preserving accuracy on the base station estimations.

In this paper, we consider the self-deployment of wireless sensor networks. We present a mechanism which allows to preserve network connectivity during the deployment of mobile wireless sensors. Our algorithm is distributed and is based on a subset of neighbours for motion decision. Our algorithm maintains a connected topology regardless of the direction chosen by each sensor. To preserve connectivity, the distance covered by the mobile nodes is constrained by the connectivity of the node to its neighbours in a connected subgraph like the relative neighbourhood graph (RNG). We show the connectivity preservation property of our algorithm through analysis and present some simulation results for the full coverage problem.

In this paper, we present for mobile ad hoc networks an efficient distributed address allocation protocol which is immune to topology changes caused by node's mobility. Contrary to the common belief that mobility makes protocol design more difficult, we show that node's mobility can, in fact, be useful to provide efficient address allocation in ad hoc networks. In our protocol, each node that has been assigned an address manages a disjoint subset of free addresses independently. By taking advantage of node mobility, we can achieve roughly even distribution of free addresses amongst nodes in the system, which enables a new joining node to be configured by its neighbors via only local communication. Theoretical analysis and extensive simulation results are presented. We show that most of the address allocation requests can be processed in a timely fashion via local communication in the requester's neighborhood with time and message complexity in the order of node's degree, regardless of the network size.

This paper considers the problem of designing power efficient routing with guaranteed delivery for sensor networks with known distances between neighbors but unknown geographic locations. We propose Hector, a hybrid energy efficient tree-based optimized routing protocol, based on two sets of virtual coordinates. One set is based on rooted tree coordinates, and the other is based on hop distances toward several landmarks. In our algorithm, the node currently holding the packet forwards it to its neighbor that optimizes ratio of power cost over distance progress with landmark coordinates, among nodes that reduce landmark coordinates and do not increase tree coordinates. If such a node does not exist then forwarding is made to the neighbor that reduces tree based distance and optimizes power cost over tree distance progress ratio. Our simulations show the superiority of our algorithm over existing alternatives while guaranteeing delivery, and only up to 30% additional power compared to centralized shortest weighted path algorithm.

In the widely used 802.11 standard, the so-called performance anomaly is a well-known issue. Several works have tried to solve this problem by introducing mechanisms such as packet fragmentation, backoff adaptation, or packet aggregation during a fixed time interval. In this paper, we propose a novel approach solving the performance anomaly problem by packet aggregation using a dynamic time interval, which depends on the busy time of the wireless medium. Our solution differs from other proposition in the literature because of this dynamic time interval, which allows increasing fairness, reactivity, and in some cases efficiency. In this article, we emphasize the performance evaluation of our proposal.

In MANET, the hidden terminals problem is a common situation which leads to poor performances due to collisions and unfairness behavior of nodes. The use of RTS/CTS mechanism is helpful to improve the performances but not sufficient: it is important to design new backoff algorithms. But, before, it is necessary to understand how backoff algorithms deal with long-term and short-term unfairness and also with performances. In this paper, based on a stochastic process algebra, we provide a new study of the hidden terminals problem. The binary exponential backoff and the double increase double decrease backoff algorithms are studied in depth in this case. The state of the medium (idle, occupied by either collision or transmission) is computed and the probability of the different backoff's stage is analysed. The short-term unfairness is clearly shown with a new metric. All results are given in both basic access and RTS/CTS one