The trajectory localisation of human activities using signal analytics has become a reality due to the widespread use of advanced signal processing systems. Device‐free localisation using WiFi devices is prevalent, and the received signal strength indicator (RSSI) and channel state information (CSI) signals offer additional benefits. However, radio frequency (RF) localisation is highly dependent on the environment, so updating fingerprint data is necessary by changing the environment. This work presents Fine‐grained Indoor Detection and Angular Radar for recognising and locating humans using a multipath trajectory reflections system that does not require training. It estimates location using a probabilistic approach that considers changes in CSI and RSSI across multiple nodes, generating an informative dataset that reflects the current trajectory and status of the location. The presented method extracts data from clustered Raspberry Pi 4B and Nexmon. The method exhibits a versatile real‐time location‐tracking solution by utilising the distinctive properties of RF signals. This technology has significant implications for various applications, including human medical monitoring, gaming, smart cities, and optimising building layouts to improve efficiency. The model demonstrates location‐independent localisation with up to 80% accuracy in mapping trajectories at any location. The findings indicate that the proposed model is effective and reliable for indoor localisation and activity tracking, making it a promising solution for implementation in real‐world environments.

This work presents a multipath trajectory reflections system called FIDAR, which uses a probabilistic approach that considers changes in channel state information and received signal strength indicator WiFi across multiple nodes to recognise and locate humans without training, and demonstrates up to 80% accuracy in mapping trajectories at any location, making it a promising solution for indoor localisation and activity tracking applications.image

Communication architectures based on the Internet of Things (IoT) are increasingly frequent. Commonly, these solutions are used to carry out control and monitoring activities. It is easy to find cases for manufacturing, prediction maintenance, Smart Cities, etc., where sensors are deployed to capture data that is sent to the cloud through edge devices or gateways. Then that data is processed to provide useful information and perform additional actions if required. As crucial as deploying these monitoring solutions is to verify their operation. In this article, we propose a novel warning method to monitor the performance of IoT‐based systems. The proposal is based on a holistic quality model called Quality of X (QoX). QoX refers to the use of a variety of metrics to measure system performance at different quality dimensions. These quality dimensions are data (Quality of Data, QoD), information (Quality of Information, QoI), users' experience (Quality of user Experience, QoE), and cost (Quality Cost, QC). In addition to showing the IoT system performance in terms of QoX in real‐time, our proposal includes (i) a forecasting model for independent estimation of QoX applying Deep Learning (DL), specifically using a Long Short‐Term Memory (LSTM) and time series, and (ii) the warning system. In light of our results, our proposal shows a better capacity to forecast quality drops in the IoT‐based monitoring system than other solutions from the related literature.

As crucial as deploying IoT‐based monitoring solutions is to verify their operation. In this paper, we propose a novel warning method to monitor and forecast quality drops in the performance of IoT‐based systems using deep learning. Quality is addressed holistically, encompassing four dimensions known as Quality of Data, Quality of Information, Quality of user Experience, and Quality Cost.image

A closed‐form solution for localising and synchronising an acoustic sensor node with respect to a Wireless Acoustic Sensor Network (WASN) is presented. The aim is to allow efficient scaling of a WASN by individually calibrating newly joined sensor nodes instead of recalibrating the entire array. A key contribution is that the sensor to be calibrated does not need to include a built‐in emitter. The proposed method uses signals emitted from spatially distributed sources to compute time difference of arrival (TDOA) measurements between the existing WASN and a new sensor. The problem is then modelled as a set of multivariate non‐linear TDOA equations. Through a simple transformation, the non‐linear TDOA equations are converted into a system of linear equations. Then, weighted least squares is applied to find an accurate estimate of the calibration parameters. Signal sources can either be known emitters within the existing WASN or arbitrary sources in the environment, thus allowing for flexible applicability in both active and passive calibration scenarios. Simulation results under various conditions show high joint localisation and synchronisation performance, often compared to the Cramér‐Rao lower bound.

This study proposes a closed‐form solution for localising and synchronizing a new acoustic sensor node with a WASN by using signals emitted from spatially distributed sources. The proposed method does not require a built‐in emitter in the sensor to be calibrated, and it can use both known emitters within the existing WASN and arbitrary sources in the environment. Simulation results show high joint localisation and synchronisation performance, often comparable to the CRLB, allowing for efficient scaling of a WASN by individually calibrating newly joined sensor nodes instead of recalibrating the entire array.image