1,721,002 research outputs found
Multitarget detection/tracking for monostatic ground penetrating radar: Application to pavement profiling
No full textMonostatic ground penetrating radar (GPR) has proven to be a useful technique in pavement profiling. In road and highway pavements, layer thickness and permittivity of asphalt and concrete can be estimated by using an inverse scattering approach. Layer-stripping inversion refers to the iterative estimation of layer properties from amplitude and time of delay (TOD) of echoes after their detection. This method is attractive for realtime implementation, in that accuracy is improved by reducing false alarms. To make layer stripping useful, a multitarget detection/tracking (D/T) algorithm is proposed. It exploits the lateral continuity of echoes arising from a multilayered medium. Interface D/T means that both detection and tracking are employed simultaneously (not sequentially). For each scan, both detection of the target and tracking of the corresponding TOD of the backscattered echoes are based on the evaluated a posteriori probability density. The TOD is then estimated by using the maximum a posteriori (MAP) or the minimum mean square error (MMSE) criterion. The statistical properties of a scan are related to those of the neighboring ones by assuming, for the interface, a first-order Markov model. © 1999 IEEE
Bayesian Algorithms for Indoor Radio Localization
No full textLocalization of moving users or terminals (MTs) is one of the hottest topics in mobile radio/network research and development. User localization may be achieved by satellites (eg using the GPS or the forthcoming GALILEO satellite system) or radio. While in the first case one or more additional devices must be embedded in the user terminal, thus making it more complex and expensive, the latter scenario requires no additional devices since only radio/network services are employed. Radio-assisted ocalization is the only method suitable in indoor or urban canyon scenarios where satellite signals are not available
Multitarget detection/tracking based on hidden Markov models
No full textIn several remote sensing applications, multitarget detection/tracking (D/T) of the backscattered wavefields is a very demanding task. Wavefield signals, sampled by an array of sensors, can be described by an hidden Markov model (HMM). As a consequence, the time of delay (TOD) profiles for each of the wavefield (or target) can be estimated by any of the known methods for state-sequence estimation such as the Viterbi (VA) and the backward/forward (BFA) algorithms. Some assumptions, that arise in the wavefield separation problem, allow one to include some additional constraints that preserve the target/tracker association. When an improved resolution is required, the choice of the multitarget Viterbi algorithm (MVA) is mandatory even if its complexity increases exponentially
A jump Markov particle filter for localization of moving terminals in multipath indoor scenarios
No full textThis paper describes an efficient Bayesian framework for localization of moving terminals (MT) in wideband wireless networks. In a previous paper, the authors have presented a grid-based technique, based on a hidden Markov model, that used the power delay profiles of the received signals to track the MT position. This grid-based Bayesian method has proved its efficacy in reducing localization errors in realistic indoor environments with multipath effects and mixed line-of-sight/non line-of-sight (LOS/NLOS) conditions. However, the computational power and the memory storage requirements limit its use in practical wireless networks. To improve the computational efficiency, here we propose a jump-Markov particle-filter approach as an extension of the previous work; the LOS/NLOS sight process is the jumping feature that drives the MT motion dynamics, while the particle filter is used to track the MT position. Performance analyses, carried out for realistic multipath indoor environments, show that, with respect to the previous grid-based algorithm, this novel approach greatly reduces the tracking filter complexity still preserving the same localization accuracy. Simulation results prove also the robustness of the proposed method with respect to the uncertainty of sight statistics information
Hidden Markov Model for multidimensional wavefront tracking
No full textIn subsurface sensing, the estimation of the delays (wavefronts) of the backscattered wavefields is a very time-consuming, mostly manual task. We propose delay estimation by exploiting the continuity of the wavefronts modeled as a Markov chain. Each wavefront is a realization of Brownian motion with a correlation that depends on the distance between each source/receiver pair. Therefore, the delay profiles can be tracked with any known method by assuming that the ordered sequence of signals is described by a hidden Markov model (HMM). Linear array provides the most natural data-ordering, and in this case the tracking algorithms can preserve the target/tracker association. However, when measurements are multidimensional, the volume-slicing strategies, that are able to get a linear array of (virtually) ordered signals, select the measurements independently of the target. When different estimates along slices are merged mis-ties can occur easily. Since data-ordering is a main issue for irregularly positioned sources and receivers, we propose a region growing tracking technique that orders (for each specified target) the data while tracking. The ordering is based on the maximum a posteriori probability of detection. Experiments based on multidimensional measurements show that this region growing tracking algorithm based on HMM preserves the target/tracker association
Electromagnetic Models for Device-Free Radio Localization with Antenna Arrays
No full textDevice-Free Localization (DFL) techniques are able to detect and localize people that do not need to wear any electronic devices. DFL systems, based on Radio Frequency (RF) nodes, employ a network of radio devices, typically equipped with a single antenna, that measure the attenuation introduced by the bodies located inside the monitored area to estimate their positions. To this aim, several physical, statistical and electromagnetic (EM) models have been introduced in the literature to relate the body positions to the RF signals received by the nodes. This paper develops an EM body model suitable for application to DFL systems relying on devices equipped with multiple antennas. In particular, the proposed EM body model describes the multi-link geometry found in array processing scenarios. The array-based body model, based on the scalar diffraction theory, is compared against the results obtained using an EM simulator to validate its prediction capabilities. The proposed model paves the way for a wider use of multi-antenna systems and novel beamforming algorithms for DFL array-based applications
Bag-of-Words Similarity in eXplainable AI
No full texteXplainable AI (XAI) does not only lie in the interpretation of the rules generated by AI systems, but also in the evaluation and selection, among many rules automatically generated by large datasets, of those that are more relevant and meaningful for domain experts. With this work, we propose a method for evaluation of similarity between rules, which identifies similar rules, or very different ones, by exploiting techniques developed for Natural Language Processing (NLP). We evaluate the similarity of if-then rules by interpreting them as sentences and generating a similarity matrix acting as an enabler for domain experts to analyse the generated rules and thus discover new knowledge. Rule similarity may be applied to rule analysis and manipulation in different scenarios: the first one deals with rule analysis and interpretation, while the second scenario refers to pruning unnecessary rules within a single ruleset. Rule similarity allows also the automatic comparison and evaluation of rulesets. Two different examples are provided to evaluate the effectiveness of the proposed method for rules analysis for knowledge extraction and rule pruning
Electromagnetic Models for Passive Detection and Localization of Multiple Bodies
Full text linkThis article proposes a multibody electromagnetic (EM) model for the quantitative evaluation of the influence of multiple human bodies in the surroundings of a radio link. Modeling of human-induced fading is the key element for the development of real-time device-free (or passive) localization (DFL) and human presence-aware systems (HPS) based on the processing of the received signal strength (RSS) data recorded by radio frequency devices. The proposed physical–statistical model is able to relate the RSS measurements to the position, size, orientation, and random movements of people located in the link area. This novel EM model is thus instrumental for crowdsensing, occupancy estimation, and people counting applications for indoor and outdoor scenarios. This article presents the complete framework for the generic N-body scenario where the proposed EM model is based on the knife-edge approach that is generalized here for multiple targets. The EM-equivalent size of each target is then optimized to reproduce the body-induced alterations of the free-space radio propagation. The predicted results are then compared against the full EM simulations obtained with a commercially available simulator. Finally, experiments are carried out to confirm the validity of the proposed model using IEEE 802.15.4-compliant industrial radio devices
Electromagnetic-Informed Generative Models for Passive RF Sensing and Perception of Body Motions
No full textElectromagnetic (EM) body models predict the impact of human presence and motions on the Radio-Frequency (RF) field originated from wireless devices nearby. Despite their accuracy, EM models are time-consuming methods which prevent their adoption in strict real-time computational imaging and estimation problems, such as passive localization, RF tomography, and holography. Physicsinformed Generative Neural Network (GNN) models have recently attracted a lot of attention thanks to their potential to reproduce a process by incorporating relevant physical laws and constraints. They can be used to simulate or reconstruct missing data or samples, reproduce EM propagation effects, approximated EM fields, and learn a physics-informed data distribution, i.e., the Bayesian prior. Generative machine learning represents a multidisciplinary research area weaving together physical/EM modelling, signal processing, and Artificial Intelligence (AI). The paper discusses two popular techniques, namely Variational Auto-Encoders (VAEs) and Generative Adversarial Networks (GANs), and their adaptations to incorporate relevant EM body diffraction methods. The proposed EM-informed GNN models are verified against classical EM tools driven by diffraction theory, and validated on real data. The paper explores emerging opportunities of GNN tools targeting real-time passive RF sensing in communication systems with dense antenna arrays. Proposed tools are also designed, implemented, and verified on resource constrained wireless devices. Simulated and experimental analysis reveal that GNNs can limit the use of time-consuming and privacy-sensitive training stages as well as intensive EM computations. On the other hand, they require hyper-parameter tuning to achieve a good compromise between accuracy and generalization
- …
