Identification of line-of-sight (LOS) and non-line-of-sight (NLOS) propagation conditions is very useful in ultra wideband localization systems. In the identification, supervised machine learning is often used, but it requires exorbitant efforts to maintain and label the LOS and NLOS database. In this paper, we apply unsupervised machine learning approach called ''expectation maximization for Gaussian mixture models'' to classify LOS and NLOS components. The key advantage of applying unsupervised machine learning is that it does not require any rigorous and explicit labeling of the database at a certain location. The simulation results demonstrate that by using the proposed algorithm, LOS and NLOS signals can be classified with 86.50% correct rate, 12.70% false negative, and 0.8% false positive rate. We also compare the proposed algorithm with the existing cutting-edge supervised machine learning algorithms in terms of computational complexity and signals' classification performance. INDEX TERMS Expectation maximization, Gaussian mixture models, unsupervised machine learning, ultra wideband systems, non-line-of-sight identification.
An optical probe of cesium Rydberg atoms generated in a thermal vapor cell is used to retrieve a baseband signal modulated onto a 16.98-GHz carrier wave in real-time, demonstrating an atombased quantum receiver suitable for microwave communication. The 60S 1/2 Rydberg level of cesium atoms in the cell is tracked via electromagnetically induced transparency (EIT), an established laser-spectroscopic method. The microwave carrier is resonant with the 60S 1/2 → 60P 1/2 Rydberg transition, resulting in an Autler-Townes (AT) splitting of the EIT signal. Amplitude modulation of the carrier wave results in a corresponding modulation in the optically retrieved AT splitting. Frequency modulation causes a change in relative height of the two AT peaks, which can be optically detected and processed to retrieve the modulation signal. The optical retrieval of the baseband signal does not require electronic demodulation. The method is suitable for carrier frequencies within a range from ∼ 1 GHz to hundreds of GHz. The baseband bandwidth, which is ∼ 20 Hz in the present demonstration, can be increased by faster spectroscopic sampling.1 THz [7], including measurements of microwave (MW) fields [8] and their polarizations [9], and millimeter waves [10]. Small Rydberg-atom field sensors that employ µm-length vapor cells and hollow-core fibers [11] offer significant potential for miniaturization. Recently, Rydberg atoms have also been explored as sensitive, high bandwidth, atomic communications receivers for digital communication [12]. Rydberg atoms have many electronic states with a large number of electric-dipole transitions between them [2], leading to a strong electromagnetic response of these atoms at a dense set of frequencies within the MHz-to THz-range. Rydberg-atom-based field detectors can have a higher sensitivity than detectors with traditional dipole antennas [13], making them suitable for long-distance communication with potential for high-speed parallel operation. In addition, Rydberg atomic receivers can be used for subwavelength imaging of microwave electric-field distributions [14,15].
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.