In the evolving sixth generation (6G) landscape, the integration of reconfigurable intelligent surfaces (RIS) with unmanned aerial vehicles (UAVs) offers a revolutionary opportunity to optimize data collection in the Internet of things (IoT) through deep reinforcement learning (DRL) and improve energy efficiency and network performance. This paper aims to study how reconfigurable intelligent surfaces and deep reinforcement learning can help increase throughput and energy efficiency in unmanned aerial vehicle-controlled Internet of things networks. The focus is on improving the capabilities of unmanned aerial vehicles to efficiently collect data in different regions and ensure safe landings. Divided into two phases, the study first improves the directional capacity and flexibility of unmanned aerial vehicles and then evaluates the integration of reconfigurable intelligent surface technology. We introduce two deep reinforcement learning models, namely the directional capacity and flexible reconnaissance (DCFR) model and the reconfigurable intelligent surface model, and compare them with a benchmark model. We found significant improvements in communication and data collection efficiency. The simulation results show an 8.18% increase in data collection performance and a 6.92% increase in collected data per unit energy when using reconfigurable intelligent surfaces, with a 10.59% increase in collection performance and a 22.64% increase in energy efficiency. Furthermore, an unmanned aerial vehicle optimized with the double deep Q-network algorithm effectively identified optimal trajectories for data collection, confirming the significant benefits of reconfigurable intelligent surfaces in unmanned aerial vehicle-controlled Internet of things networks.

The deployment and maintenance of large smart infrastructures used for powering data-driven decision making, regardless of retrofitted or newly deployed infrastructures, still lack automation and mostly rely on extensive manual effort. In this article, we focus on the two main challenges in the lifecycle of smart infrastructures: deployment and operation, each of which is rather generic and applies to all infrastructures. We discuss the existing technologies designed to help improve and automate deployment and operation for smart infrastructures in general and use the smart grid as a guiding example to ground some examples across the article. Next, we identify and discuss opportunities where the broad field of artificial intelligence (AI) can help further improve and automate the lifecycle of smart infrastructures to eventually improve their reliability and drive down their deployment and operation costs. Finally, based on the usage of AI for web and social networks as well as our previous experience in AI for networks and cyber-physical systems, we provide decision guidelines for the adoption of AI.

Today, there are billions of connected IoT devices and their number continues to grow as they contribute to the digitalization of infrastructures. However, the deployment process of these smart wireless devices when delivered to customer premises is slow and error prone as each of them needs to be provisioned with authentication credentials to access the corporate network. In this paper, we propose HANNA, a humanfriendly provisioning and configuration framework for smart devices, that extends the zero-touch paradigm to large IoT deployments by introducing voice assisted configuration in combination with large scale ad-hoc communications to overcome the initial installation effort of IoT deployments. The most prominent role in HANNA is played by the assisting device, which includes a voice assistant capable of correctly understanding a minimum number of keywords required for initial provisioning and configuration of the devices. The device's role is to interact with the user and ensure that all provisioning details are received. These are then converted into appropriate machine instructions for further use by the mass provisioning mechanism. We provide an example prototype implementation of HANNA and evaluate the performance of the assisting device in the human-to-machine communication phase and the performance of the selected communication technique in the machine-to-machine communication phase. Our results show the potential of existing speech-to-text engines for this application area and also reveal shortcomings with respect to the robustness of the engines in office-like working environments as well as with respect to user's gender and language proficiency level. Additionally we show that the proposed machine-to-machine provisioning approach is always faster compared to manual provisioning for cases with more than ten devices.

The concept of the “connected car” offers the potential for safer, more enjoyable and more efficient driving and eventually autonomous driving. However, in urban Vehicular Networks (VNs), the high mobility of vehicles along roads poses major challenges to the routing protocols needed for a reliable and flexible vehicular communications system. Thus, urban VNs rely on static Road-Side-Units (RSUs) to forward data and to extend coverage across the network. In this paper, we first propose a new Q-learning-based routing algorithm, namely Infrastructure-aided Traffic-Aware Routing (I-TAR), which leverages the static wired RSU infrastructure for packet forwarding. Then, we focus on the multi-source, multi-destination problem and the effect this imposes on node availability, as nodes also participate in other communications paths. This motivates our new hybrid approach, namely Hybrid Infrastructure-aided Traffic Aware Routing (HI-TAR) that aims to select the best Vehicle-to-Vehicle/Infrastructure (V2V/I) route. Our findings demonstrate that I-TAR can achieve up to 19% higher average packet-delivery-ratio (APDR) compared to the state-of-the-art. Under a more realistic scenario, where node availability is considered, a decline of up to 51% in APDR performance is observed, whereas the proposed HI-TAR in turn can increase the APDR performance by up to 50% compared to both I-TAR and the state-of-the-art. Finally, when multiple source-destination vehicle pairs are considered, all the schemes that model and consider node availability, i.e. limited-availability, achieve from 72.2% to 82.3% lower APDR, when compared to those that do not, i.e. assuming full-availability. However, HI-TAR still provides 34.6% better APDR performance than I-TAR, and ~40% more than the state-of-the-art.

Machine learning (ML) techniques play a significant role in detecting abnormal link operations in wireless networks. However, during the design and development process of a ML-based model, numerous factors including input data transformation, scaling methods, choice of ML techniques and their associated parametrization, influence the final model performance. In this paper, we discuss the design and development process of wireless link anomaly detection models followed by the model ranking process for selecting the most suitable models given the required application criteria. Under this premise, we consider four different data representations, four anomaly types, six scaling methods and six distinct ML techniques along with their associated parametrization trials leading to over twenty thousand anomaly detection models for wireless links. We show that the most suitable supervised ML models are able to detect anomalies with an F1 score of at least 88% and up to perfect score, whereas unsupervised ML models can attain an F1 score of up to 96% depending on the anomaly type, and on average, amongst 20,352 available models, the supervised SVM model can be readily adopted to efficiently detect any type of anomaly with an F1 score of at least 94%, particularly when trained on encoded data representations using the combination of "mean and deviation scaling" and "non-linear RBF kernel".

Since the emergence of wireless communication networks, a plethora of research papers focus their attention on the quality aspects of wireless links. The analysis of the rich body of existing literature on link quality estimation using models developed from data traces indicates that the techniques used for modeling link quality estimation are becoming increasingly sophisticated. A number of recent estimators leverage machine learning (ML) techniques that require a sophisticated design and development process, each of which has a great potential to significantly affect the overall model performance. In this paper, we provide a comprehensive survey on link quality estimators developed from empirical data and then focus on the subset that use ML algorithms. We analyze ML-based link quality estimation (LQE) models from two perspectives using performance data. Firstly, we focus on how they address quality requirements that are important from the perspective of the applications they serve. Secondly, we analyze how they approach the standard design steps commonly used in the ML community. Having analyzed the scientific body of the survey, we review existing open source datasets suitable for LQE research. Finally, we round up our survey with the lessons learned and design guidelines for ML-based LQE development and dataset collection.

Machine learning (ML) has been used to develop increasingly accurate link quality estimators for wireless networks. However, more in depth questions regarding the most suitable class of models, most suitable metrics and model performance on imbalanced datasets remain open. In this paper, we propose a new tree based link quality classifier that meets high performance and fairly classifies the minority class and, at the same time, incurs low training cost. We compare the tree based model, to a multilayer perceptron non-linear model and two linear models, namely logistic regression and support vector machine, on a selected imbalanced dataset and evaluate their results using five different performance metrics. Our study shows that 1) non-linear models perform slightly better than linear models in general, 2) the proposed non linear tree-based model yields the best performance trade-off considering F1, training time and fairness, 3) single metric aggregated evaluations based only on accuracy can hide poor, unfair performance especially on minority classes, and 4) it is possible to improve the performance on minority classes, by over 40% through feature selection and by over 20% through resampling, therefore leading to fairer classification results.

Relying on multi-hop communication techniques, aeronautical ad hoc networks (AANETs) seamlessly integrate ground base stations (BSs) and satellites into aircraft communications for enhancing the on-demand connectivity of planes in the air. The goal of the paper is to assess the performance of the classic shortest-path routing algorithm in the context of the real flight data collected in the North-Atlantic Region. Specifically, in this integrated AANET context we investigate the shortest-path routing problem with the objective of minimizing the total delay of the in-flight connection from the ground BS subject to certain minimum-rate constraints for all selected links in support of low-latency and high-speed services. Inspired by the best-first search and priority queue concepts, we model the problem formulated by a weighted digraph and find the optimal route based on the shortest-path algorithm. Our simulation results demonstrate that aircraft-aided multi-hop communications are capable of reducing the total delay of satellite communications, when relying on real historical flight data.

With the evolution of mobile communications towards fifth-generation (5G) and beyond, all layers of the wireless networks are increasingly virtualized and software-controlled using automated tools. DevOps tools enabling smooth and fast testing through continuous integration (CI) and rapid deployment through continuous delivery (CD) of the software in cloud environments are permeating also communication infrastructures, eventually leading to the so-called “zero-touch network automation”. Such automation frameworks have been actively used in wireless testing infrastructures, such as FIRE and GENI. For instance, the continuous integration in wireless (COINS) technology development framework has been used in the LOG-a-TEC testbed facility of the FIRE federation. In this paper, we propose a task-based operational structure of COINS for a thorough evaluation of the time for operation (TFO) performance of each task. Moreover, we analyse the impact of different experiments and the number of nodes participating in the experiment on the TFO performance of the COINS framework. The results; i) demonstrate that the device tasks within COINS framework are the bottleneck occupying up to 92.6% of the total TFO, and ii) reveal that the TFO performances of the receive details task on the device side and the gather results task on the server side are significantly diminished with the increased number of nodes participating in the same type of experiment.

In the event of a natural disaster, arrival time of the search and rescue (SAR) teams to the affected areas is of vital importance to save the life of the victims. In particular, when an earthquake occurs in a geographically large area, reconnaissance of the debris within a short-time is critical for conducting successful SAR missions. An effective and quick situational awareness in postdisaster scenarios can be provided via the help of unmanned aerial vehicles (UAVs). However, off-the-shelf UAVs suffer from the limited communication range as well as the limited airborne duration due to battery constraints. If telecommunication infrastructure is destroyed in such a disaster, maximum coverage to be monitored by a ground station (GS) using UAVs is limited to a single UAV?s wireless coverage regardless of how many UAVs are deployed. Additionally, performing a blind search within the affected area could induce significant delays in SAR missions and thus leading to inefficient use of the limited battery energy. To address these issues, we develop a multiagent Q-learning based trajectory planning algorithm that maintains all-time connectivity towards the GS in a multihop manner and enables UAVs to observe as many critical areas (highly populated areas) as possible. The comprehensive experimental results demonstrate that the proposed multiagent Q-learning algorithm is capable of attaining UAV trajectories that can cover significantly larger portions of the critical areas summing up to 43% than that of the existing algorithms, such as the extended versions of Monte Carlo, greedy and random algorithms.

Integrated ground-air-space (IGAS) networks intrinsically amalgamate terrestrial and non-terrestrial communication techniques in support of universal connectivity across the globe. Multi-hop routing over the IGAS networks has the potential to provide long-distance highly directional connections in the sky. For meeting the latency and reliability requirements of in-flight connectivity, we formulate a multi-objective multi-hop routing problem in aeronautical ad hoc networks (AANETs) for concurrently optimizing multiple end-to-end performance metrics in terms of the total delay and the throughput. In contrast to single-objective optimization problems that may have a unique optimal solution, the problem formulated is a multi-objective combinatorial optimization problem (MOCOP), which generally has a set of trade-off solutions, called the Pareto optimal set. Due to the discrete structure of the MOCOP formulated, finding the Pareto optimal set becomes excessively complex for large-scale networks. Therefore, we employ a multi-objective evolutionary algorithm (MOEA), namely the classic NSGA-II for generating an approximation of the Pareto optimal set. Explicitly, with the intrinsic parallelism of MOEAs, the MOEA employed starts with a set of candidate solutions for creating and reproducing new solutions via genetic operators. Finally, we evaluate the MOCOP formulated for different networks generated both from simulated data as well as from real historical flight data. Our simulation results demonstrate that the utilized MOEA has the potential of finding the Pareto optimal solutions for small-scale networks, while also finding a set of high-performance nondominated solutions for large-scale networks.

Machine learning (ML) techniques play a significant role in detecting anomalous wireless links. However, to date, to the extent of our knowledge, there is no robust classifier that would work in a realistic scenario where various anomalies could appear concurrently in the time-series gleaned from the network monitoring tools. In this paper, we propose a new deep learning based classifier and show that is able to outperform the state of the art for existing link layer anomalies. Our evaluation results demonstrate that the state-of-the ML models perform with an average accuracy of about 63%, whereas the average accuracy of the proposed DL model is around 90%, indicating a significant improvement of 27 percentage points anomaly detection performance.

Ensuring a reliable communication in wireless networks strictly depends on the effective estimation of the link quality, which is particularly challenging when propagation environment for radio signals significantly varies. In such environments, intelligent algorithms that can provide robust, resilient and adaptive links are being investigated to complement traditional algorithms in maintaining a reliable communication. In this respect, the data-driven link quality estimation (LQE) using machine learning (ML) algorithms is one of the most promising approaches. In this paper, we provide a quantitative evaluation of design decisions taken at each step involved in developing a ML-based wireless LQE on a selected, publicly available dataset. Our study shows that, re-sampling to achieve training class balance and feature engineering have a larger impact on the final performance of the LQE than the selection of the ML method on the selected data.

The Internet of Things (IoT) is being widely adopted in today's society, interconnecting smart embedded devices that are being deployed for indoor and outdoor environments, such as homes, factories and hospitals. Along with the growth in the development and implementation of these IoT devices, their simple and rapid deployment, initial configuration and out-of-the-box operational provisioning are becoming prominent challenges to be circumvented. Considering a large number of heterogeneous devices to be deployed within next generation IoT networks, the amount of time needed for manual provisioning of these IoT devices can significantly delay the deployment and manual provisioning may introduce human-induced failures and errors. By incorporating zero-touch provisioning (ZTP), multiple heterogeneous devices can be provisioned with less effort and without human intervention. In this paper, we propose software-enabled access point (Soft-AP)- and Bluetooth-based ZTP solutions relying only on a single mediator device and evaluate their performances using LOG-A-TEC testbed against manual provisioning in terms of the time required for provisioning (time-to-provision, TTP). We demonstrate that on average, Soft-AP- and Bluetooth-based ZTP solutions outperform manual provisioning with about 154% and 313% when compared to the expert provisioning, and with about 434% and 880% when compared to the non-expert provisioning in terms of TTP performances, respectively.

After decades of research, Internet of Things (IoT) is finally permeating real-life and helps improve the efficiency of infrastructures and processes as well as our health. As massive number of IoT devices are deployed, they naturally incurs great operational costs to ensure intended operations. To effectively handle such intended operations in massive IoT networks, automatic detection of malfunctioning, namely anomaly detection, becomes a critical but challenging task. In this paper, motivated by a real-world experimental IoT deployment, we introduce four types of wireless network anomalies that are identified at the link layer. We study the performance of threshold- and machine learning (ML)-based classifiers to automatically detect these anomalies. We examine the relative performance of three supervised and three unsupervised ML techniques on both non-encoded and encoded (autoencoder) feature representations. Our results demonstrate that; i) selected supervised approaches are able to detect anomalies with F1 scores of above 0.98, while unsupervised ones are also capable of detecting the said anomalies with F1 scores of, on average, 0.90, and ii) OC-SVM outperforms all the other unsupervised ML approaches reaching at F1 scores of 0.99 for SuddenD, 0.95 for SuddenR, 0.93 for InstaD and 0.95 for SlowD.

We propose electronic voting authentication scheme, which is a key management mechanism for electronic voting system intended to limit the number of attacks on a polling station and strengthen the security control. The motivation is to diversify security requirements of messages exchanged between polling stations. There are different types of messages exchanged between polling stations and each type of message has different security needs. A security mechanism developed on the basis of a single key is not enough to ensure the diverse security needs of voting network. In electronic voting authentication scheme, every polling station is responsible to support three different types of keys. These are global key, pairwise key, and individual key. The global keys are public keys shared with all polling stations in the voting network. The pairwise key can be used for communication with polling stations. Individual keys will be used for communication with the server. To ensure authentication of local broadcast, electronic voting authentication scheme uses one-way key chains in a well-organized way. The support of source authentication is a visible advantage of this scheme. We examine the authentication of electronic voting authentication scheme on numerous attack models. The measurement demonstrates that electronic voting authentication scheme is very operative in protecting against numerous elegant attacks such as wormhole attack, Sybil attack, and HELLO Flood attack. The proposed system is evaluated and the results demonstrate that the proposed system is practical and secure as compared to the direct recording electronic and manual systems.

Uplink transmissions, within coexisting distinct sub-GHz technologies operating in the same unlicensed band, can be exposed to detrimental impact of the interference. In such scenarios, transmission scheduling becomes important for mitigating interference or minimizing the impact of the interference. For this purpose, we aim to whitelist relatively better channels in terms of their yielded packet reception ratio using our proposed channel quality metric that is based on the received signal-to-interference-plus-noise ratio. In this paper, we investigate the trade-offs of the channel whitelisting in random frequency division multiple access (RFDMA) networks in the presence of the cumulative intra- and inter-technology interferences. Our main findings indicate that, although channel whitelisting reduces the degree of freedom, and thus the overall capacity, it empowers a certain amount of devices to be served at a much lower received signal power, whereas this is infeasible for non-whitelisting scenarios at larger received signal power, which signifies the energy conservation ability of our proposed whitelisting method. It is experimentally demonstrated, on Sigfox, a particular type of RFDMA network, that non-whitelisting scenarios are not capable of supporting any devices at a received signal power below -118 dBm. Even for lower received signal power, we are able to reduce the required number of retransmissions at the same reception probability, which indeed indicates that the overall reliability of the network is improved.

Deploying unmanned aerial vehicle (UAV) swarms in delivery systems are still in its infancy with regard to the technology, safety, and aviation rules and regulations. Optimal use of UAVs in dynamic environments is important in many aspects, e.g., increasing efficacy and reducing the air traffic, resulting in a safer environment, and it requires new techniques and robust approaches based on the capabilities of UAVs and constraints. This paper analyzes several delivery schemes within a platform, such as delivery with and without using air highways and delivery using a hybrid scheme along with several delivery methods (i.e., optimal, premium, and first-in first-out) to explore the use of UAV swarms as part of the logistics operations. In this platform, a dimension reduction technique, "dynamic multiple assignments in multidimensional space," and several other new techniques along with Hungarian and cross-entropy Monte Carlo techniques are forged together to assign tasks and plan 3D routes dynamically. This particular approach is performed in such a way that UAV swarms in several warehouses are deployed optimally given the delivery scheme, method, and constraints. Several scenarios are tested on the simulator using small and big data sets. The results show that the distribution and the characteristics of data sets and constraints affect the decision on choosing the optimal delivery scheme and the method. The findings are expected to guide the aviation authorities in their decisions before dictating rules and regulations regarding effective, efficient, and safe use of UAVs. Furthermore, the companies that produce UAVs are going to take the demonstrated results into account for their functional design of UAVs along with other companies that aim to deliver their products using UAVs. Additionally, private industries, logistics operators, and municipalities are expected to benefit from the potential adoption of the simulator in strategic decisions before embarking on the practical implementation of UAV delivery systems.

Interleaved boost converter (IBC) is equal to two-boost converter operating in parallel. IBCs are more advantageous than conventional boost converters. Input current of the interleaved converter is less fluctuated compared to that of the boost converter. In this paper, a new IBC structure is introduced unlike the conventional IBC structure. In the presented converter, the place of output filter capacitor is changed unlike the conventional IBC and thus, the voltage across the output filter capacitor is reduced about V-i. The proposed IBC performs similar experimental results compared to that of the conventional IBC. Besides, the proposed IBC enables the utilization of an output filter capacitor even with lower voltage, and thus the cost of IBC is reduced. The analysis of operating stages of the presented converter is conducted for D < 50% and D > 50% modes. Finally, an experimental setup of the presented converter is realized along with the parameters of 640 W and 20 kHz.

The recent advances in cyber-physical domains, cloud, cloudlet, and edge platforms along with the evolving Artificial Intelligence (AI) techniques, big data analytics, and cutting-edge wireless communication technologies within the Industry 4.0 (4IR) are urging mechatronics designers, practitioners, and educators to further review the ways in which mechatronics systems are perceived, designed, manufactured, and advanced. Within this scope, we introduce the service-oriented cyber-physical advanced mechatronics systems (AMSs) along with current and future challenges. The objective in AMSs is to create remarkably intelligent autonomous products by 1) forging effective sensing, self-learning, Wisdom as a Service (WaaS), Information as a Service (InaaS), precise decision making, and actuation using effective location-independent monitoring, control and management techniques with products and 2) maintaining a competitive edge through better product performances via immediate and continuous learning, while the products are being used by customers and are being produced in factories within the cycle of Automation of Everything (AoE). With the advanced wireless communication techniques and improved battery technologies, the AMSs are capable of getting independent and working with other massive AMSs to construct robust, customizable, energy-efficient, autonomous, intelligent, and immersive platforms. In this regard, rather than providing technological details, this paper implements philosophical insights into 1) how mechatronics systems are being transformed into AMSs; 2) how robust AMSs can be developed by both exploiting the wisdom created within cyber-physical smart domains in the edge and cloud platforms and incorporating all the stakeholders with diverse objectives into all phases of the product life-cycle; and 3) what essential common features AMSs should acquire to increase the efficacy of products and prolong their product life. Against this background, an AMS development framework is proposed in order to contextualize all the necessary phases of AMS development and direct all stakeholders to rivet high-quality products and services within AoE.