ABSTRACT The increasing demand for ultra‐reliable, low‐latency, and high‐throughput connectivity in dense urban environments presents significant challenges for next‐generation 6G networks. Traditional cellular networks, with their fixed cell boundaries and centralized base station control, are inadequate to meet the dynamic needs of such environments. A promising solution is the cell‐free network architecture, where a distributed set of access points (APs) jointly serve users without fixed cell boundaries. However, efficient access point selection and accurate user localization are crucial to achieving high performance in such networks. This paper presents a decentralized approach using Belief‐Desire‐Intention eXtended (BDIx) agents for dynamic AP selection and localization within a cluster‐based cell‐free 6G communications network. Various clustering algorithms (K‐means, DBSCAN, self‐organizing maps, MeanShift, ClusterGAN, and Autoencoders) are evaluated for their ability to optimize network throughput, energy efficiency, and spectral utilization. A hybrid localization framework, such as centroid‐based, differential circles, and multilateration methods, is employed to achieve accurate user positioning. The results demonstrate that machine learning‐based clustering methods, notably Gaussian mixture model (GMM), self‐organizing map (SOM), and ClusterGAN, offer significant improvements in throughput (up to 46.3%) and power reduction (up to 32.8%) over traditional methods. Regarding localization, deep learning models such as MLP, CNN, and TCN outperform deterministic methods, achieving sub‐meter accuracy with minimal errors (MeanDist < 1 m, > 0.999). Overall, the proposed solution enhances system scalability, energy efficiency, and positioning accuracy, establishing a promising foundation for future 6G networks. In our reference implementation, we instantiate the pipeline with a GMM for AP/UE clustering and a multilayer perceptron (MLP) regressor for localization.

Underwater networks are characterized by undesirable time variability of the channel conditions due to Doppler effect, serious multipath and variable impulse response. Energy efficiency is a primary concern in these scenarios, because nodes batteries cannot be recharged or replaced. Accordingly, in order to increase network lifetime and effectiveness of underwater channel transmissions, in this paper, we present a reinforcement learning approach for communication in multihop underwater networks. The proposed methodology employs a Markov underwater channel model to characterize the link status that allows the relay device to choose the most efficient next hop node to forward data towards a remote gateway device for connection to the terrestrial internet. Simulation results are presented to show the effectiveness of the proposed methodology in terms of energy consumption and latency performance so allowing to increase network lifetime.

In this paper, a software defined networking approach, named SDN-(UAV)ISE, is introduced for wireless sensor networks with data mules. In our scenario, sensor nodes are equipped with two wireless interfaces: one exploits a long range, low data rate wireless technology, such as LoRa or Sigfox, whereas the other uses a short range, wireless technology that provides higher data rate, examples include IEEE 802.15 or IEEE 802.11. Sensors can communicate directly to a control center through the long range wireless interface, or by utilizing the multihop paradigm realized with the aid of the short range wireless communication interface. In this context, a drone acts as a mobile sink (i.e., the mule) for the latter case. The movement of the data mule is forecast by the SDN controller and the forecast positions are considered to generate the flow table entries to be installed in the sensor nodes and schedule their applications. To this purpose, it is expected that the drone will move to the locations where abnormal conditions are observed by the sensors. In our work, a simple and efficient decision tree algorithm is implemented, which takes the values measured by the sensors as inputs, to forecast the route of the data mule. The proposed scheme is assessed through a large experimental campaign considering different operating conditions.

Body Area Networks (BANs) have attracted a lot of research interest in the last decades as also witnessed by standardization activities and European Commission fundings. Today, commercial devices, which implement simplified BAN monitoring have appeared, although they usually imply expensive subscription costs or need for a supporting device carried by the user (e.g. a smart phone) which, in case of elderly people, cannot be easily held. However, the integration between commercial devices and external sensors located on/in the body is still an open issue due to the limited processing capabilities of low cost commercial devices. Also, no tools for anomaly detection aimed at reliable healthcare monitoring are currently commercially available. In this paper, we focus on Cloud-Assisted BANs and evolve this vision according to the emerging paradigm of edge computing. We present design, implementation and experimentation of a wireless BAN system which performs data transmission using a commercial, cheap, off-the-shelf gateway smart watch. A mechanism for prompt anomaly detection at the edge node is also supported for the purpose of reliable healthcare monitoring as well as pre-filtering of the data at the smart device itself. Also, in order to reduce the overhead caused by propagation of useless and time-correlated data, and to guarantee a prompt action in case of emergency, edge network nodes located closer to the patient BAN are exploited since they can execute machine learning algorithms to process large amounts of data and activate potential alerts in a shorter time and without overloading the cloud. In this work we describe a real system and evaluate the effectiveness of the approach in terms of false alarm probability.

This study addresses the design of smart sensor system aided bicycle that can be exploited as a platform for the acquisition of real‐time data. In particular, in this work, the authors address the pressing issues like air pollution monitoring and health monitoring by using sensors that were seen as limitations in the already existing smart e‐bike monitoring system. The sensor system presented in this study is capable of monitoring parameters such as location, heart rate of the rider and air quality levels in real‐time. The data thus collected is fed into Thingspeak, an open Internet of Things platform powered by Matlab. The data is then visually represented in an Android application for riders to view and analyse the monitored parameters. The Android application designed for the system assists the user with location tracking, pollution mapping and health monitoring. Furthermore, security is also considered in this work which is addressed with the help of a fingerprint sensor and a global system for mobile/global positioning system module to alert the user in case of system theft. The system attached to the bicycle can be implemented on a large scale as a fleet/bike sharing system in order to map the pollution of an entire city with the help of IoT, thus aiding the development of greenfield smart city and additionally monitoring the vitals of the user riding the bicycle leading to intelligent transportation system. This study details the design and implementation of the hardware and software, enlists the outcomes of the system and explores the future scope and development.

In this study, the authors investigate the performance of a multi‐user downlink (DL) multiple‐input–multiple‐output (MIMO) system aided by polarisation multiplexing (PM) and multi‐user transmitter pre‐processing (MUTP). Dual‐ and triply‐polarised antennas that are called on to establish PM offer the advantage of replacing uni‐polarised antennas that impose space constraints. In a multi‐user scenario, users conflict multi‐user interference (MUI). In this contribution, the DL‐MUI is suppressed with the aid of pre‐processing operated at the base station. To be specific, two pre‐processing approaches are considered in their study which are based on singular value decomposition. Both the approaches exploit the channel impulse responses (CIRs) of all the users to formulate the pre‐processing matrix and that the second approach which is a joint multi‐user transmission and detection technique exploits only user specific CIRs to formulate the post‐processing matrix. In their contribution, the required CIRs for formulating the pre‐processing matrix are acquired via noisy feedback channels that endure fading as well as delay. Simulation results demonstrate that noise and fading tainted CIRs based MUTP results in performance degradation in terms of the attainable symbol‐error‐rate (SER) and sum‐capacity. Moreover, it is inferred that further degradation results when the feedback channels experience delay. However, their study shows that the application of dual or triply‐polarised antennas in conjunction with MUTP can serve as an efficient approach for the DL of the feedback MIMO system, as the achievable sum‐capacity and SER under ideal feedback remain close to that attained with the perfect CIRs hypothesis. Furthermore, it is observed that the considered MUTP techniques result in superior SER performance compared with their multi‐user detection counterpart and other widely known pre‐processing techniques.

In this correspondence, the authors study the performance of multi‐user transmitter preprocessing (MUTP)‐assisted cooperative downlink (DL) transmission for multi‐carrier code division multiple access (MC‐CDMA) system, where multi‐user interference (MUI) and inter‐relay interference (IRI) are the principal channel impairments. Relaying is facilitated with the aid of fixed infrastructure‐based relays that perform additional signal processing like formulating the preprocessing matrix for mitigating MUI in addition to forwarding the information they receive from the base station (BS). Specifically, in this study, the authors analyse the performance of cooperative communication‐aided DL MC‐CDMA system by employing three cooperation strategies: (i) all users supported by a single relay with dominant MUI at the relay and mobile stations (MSs); (ii) each user supported by a single relay where, MUI and IRI are dominant at the relays and MSs, respectively, as well as weak IRI at the MSs; and (iii) all users supported by L relays where MUI is dominant at the relays, and MUI and IRI are dominant at the MSs. Our simulation study shows that MUTP‐aided cooperative DL transmission results in better achievable bit error rate than the multi‐user detection‐aided system as the MUI at the relays and MUI and IRI at the MSs are perfectly eliminated.

Double space-time transmit diversity (DSTTD) is currently one of the promising techniques for realizing both spatial diversity and multiplexing gains concurrently. In this paper, in contrast to previous work [6], we consider the performance of double space time transmit diversity (DSTTD) system with multi-user transmitter preprocessing (MUTP) over correlated and uncorrelated frequency-selective fading channels. The transmitter preprocessing (TP) is realized by singular value decomposition (SVD) which exploits the channel state information (CSI) of all the users at the base stations (BSs). This scheme can greatly bring down the complexity of the mobile terminals as well as obviate the need for complex MUDs. Specifically, we investigate the effects of four types of delay spread distributions on MUTP assisted DSTTD system. In a multi-cell scenario, users conflict co-channel interferences (CCI) which can severely degrade the system performance. It is shown through simulation that multi-user transmitter preprocessing (MUTP) can mitigate CCI in addition to retaining the low complexity nature of the mobile terminals. Comparisons for correlated and uncorrelated frequency-selective channels with and without TP are also provided.

An efficient routing algorithm called hierarchical routing is presented in this paper. The algorithm assumes that the network is divided into logical clusters. In each cluster a so-called central controller stores the routing information and exchanges it with its neighboring central controllers. Each routing entry contains a time index which is used to react to dynamic topology changes and to minimize the amount of exchanged routing information. The presented algorithm is best suited for mobile ad hoc networks. The algorithm has been especially designed for a centralized ad hoc network HEE based on the HIPERLAN/2 standard standardized by ETSI but may be used in any ad hoc network configuration. The performance of the algorithm is analytically compared to the performance of the dynamic source routing algorithm.