The Experts below are selected from a list of 1284 Experts worldwide ranked by ideXlab platform
Shiyin Li - One of the best experts on this subject based on the ideXlab platform.
-
deep learning for signal demodulation in physical layer wireless communications prototype platform open dataset and analytics
IEEE Access, 2019Co-Authors: Hongmei Wang, Zhenzhen Wu, Songtao Lu, Han Zhang, Guoru Ding, Shiyin LiAbstract:In this paper, we investigate deep learning (DL)-enabled signal demodulation methods and establish the first open dataset of real modulated signals for wireless communication systems. Specifically, we propose a flexible communication prototype platform for measuring real modulation dataset. Then, based on the measured dataset, two DL-based Demodulators, called deep belief network (DBN)-support vector machine (SVM) demodulator and adaptive boosting (AdaBoost)-based demodulator, are proposed. The proposed DBN-SVM based demodulator exploits the advantages of both DBN and SVM, i.e., the advantage of DBN as a feature extractor and SVM as a feature classifier. In DBN-SVM based demodulator, the received signals are normalized before being fed to the DBN network. Furthermore, an AdaBoost-based demodulator is developed, which employs the $k$ -nearest neighbor as a weak classifier to form a strong combined classifier. Finally, the experimental results indicate that the proposed DBN-SVM based demodulator and AdaBoost-based demodulator are superior to the single classification method using DBN, SVM, and maximum likelihood-based demodulator.
-
signal demodulation with machine learning methods for physical layer visible light communications prototype platform open dataset and algorithms
IEEE Access, 2019Co-Authors: Songtao Lu, Han Zhang, Hang Li, Chun Du, Shiyin LiAbstract:In this paper, we investigate the design and implementation of machine learning (ML)-based demodulation methods in the physical layer of visible light communication (VLC) systems. We build a flexible hardware prototype of an end-to-end VLC system, from which the received signals are collected as the real data. The dataset is available online, which contains eight types of modulated signals. Then, we propose three ML Demodulators based on convolutional neural network (CNN), the deep belief network (DBN), and adaptive boosting (AdaBoost), respectively. Specifically, the CNN-based demodulator converts the modulated signals to images and recognizes the signals by the image classification. The proposed DBN-based demodulator contains three restricted Boltzmann machines to extract the modulation features. The AdaBoost method includes a strong classifier that is constructed by the weak classifiers with the k -nearest neighbor algorithm. These three Demodulators are trained and tested by our online open dataset. The experimental results show that the demodulation accuracy of the three data-driven Demodulators drops as the transmission distance increases. A higher modulation order negatively influences the accuracy for a given transmission distance. Among the three ML methods, the AdaBoost modulator achieves the best performance.
Adam M. Wojciechowski - One of the best experts on this subject based on the ideXlab platform.
-
precision temperature sensing in the presence of magnetic field noise and vice versa using nitrogen vacancy centers in diamond
Applied Physics Letters, 2018Co-Authors: Christian Osterkamp, Adam M. Wojciechowski, Mürsel Karadas, Jan Meijer, Steffen Jankuhn, A. Huck, Fedor Jelezko, Ulrik L AndersenAbstract:We demonstrate a technique for precision sensing of the temperature or the magnetic field by simultaneously driving two hyperfine transitions involving distinct electronic states of the nitrogen-vacancy center in diamond. Frequency modulation of both driving fields is used with either the same or opposite phase, resulting in the immunity to fluctuations in either the magnetic field or the temperature, respectively. In this way, a sensitivity of 1.4 nT Hz−1∕2 or 430 μK Hz−1∕2 is demonstrated. The presented technique only requires a single frequency demodulator and enables the use of phase-sensitive camera imaging sensors. A simple extension of the method utilizing two Demodulators allows for simultaneous, independent, and high-bandwidth monitoring of both the magnetic field and the temperature.
-
Precision temperature sensing in the presence of magnetic field noise and vice-versa using nitrogen-vacancy centers in diamond
Applied Physics Letters, 2018Co-Authors: Adam M. Wojciechowski, Christian Osterkamp, Mürsel Karadas, Jan Meijer, Steffen Jankuhn, A. Huck, Ulrik L AndersenAbstract:We demonstrate a technique for precision sensing of temperature or the magnetic field by simultaneously driving two hyperfine transitions involving distinct electronic states of the nitrogen-vacancy center in diamond. Frequency modulation of both driving fields is used with either the same or opposite phase, resulting in the immunity to fluctuations in either the magnetic field or the temperature, respectively. In this way, a sensitivity of 1.4 nT Hz$^{-1/2}$ or 430 $\mu$K Hz$^{-1/2}$ is demonstrated. The presented technique only requires a single frequency demodulator and enables the use of phase-sensitive camera imaging sensors. A simple extension of the method utilizing two Demodulators allows for simultaneous, independent, and high-bandwidth monitoring of both the magnetic field and temperature.
Ulrik L Andersen - One of the best experts on this subject based on the ideXlab platform.
-
precision temperature sensing in the presence of magnetic field noise and vice versa using nitrogen vacancy centers in diamond
Applied Physics Letters, 2018Co-Authors: Christian Osterkamp, Adam M. Wojciechowski, Mürsel Karadas, Jan Meijer, Steffen Jankuhn, A. Huck, Fedor Jelezko, Ulrik L AndersenAbstract:We demonstrate a technique for precision sensing of the temperature or the magnetic field by simultaneously driving two hyperfine transitions involving distinct electronic states of the nitrogen-vacancy center in diamond. Frequency modulation of both driving fields is used with either the same or opposite phase, resulting in the immunity to fluctuations in either the magnetic field or the temperature, respectively. In this way, a sensitivity of 1.4 nT Hz−1∕2 or 430 μK Hz−1∕2 is demonstrated. The presented technique only requires a single frequency demodulator and enables the use of phase-sensitive camera imaging sensors. A simple extension of the method utilizing two Demodulators allows for simultaneous, independent, and high-bandwidth monitoring of both the magnetic field and the temperature.
-
Precision temperature sensing in the presence of magnetic field noise and vice-versa using nitrogen-vacancy centers in diamond
Applied Physics Letters, 2018Co-Authors: Adam M. Wojciechowski, Christian Osterkamp, Mürsel Karadas, Jan Meijer, Steffen Jankuhn, A. Huck, Ulrik L AndersenAbstract:We demonstrate a technique for precision sensing of temperature or the magnetic field by simultaneously driving two hyperfine transitions involving distinct electronic states of the nitrogen-vacancy center in diamond. Frequency modulation of both driving fields is used with either the same or opposite phase, resulting in the immunity to fluctuations in either the magnetic field or the temperature, respectively. In this way, a sensitivity of 1.4 nT Hz$^{-1/2}$ or 430 $\mu$K Hz$^{-1/2}$ is demonstrated. The presented technique only requires a single frequency demodulator and enables the use of phase-sensitive camera imaging sensors. A simple extension of the method utilizing two Demodulators allows for simultaneous, independent, and high-bandwidth monitoring of both the magnetic field and temperature.
Songtao Lu - One of the best experts on this subject based on the ideXlab platform.
-
deep learning for signal demodulation in physical layer wireless communications prototype platform open dataset and analytics
IEEE Access, 2019Co-Authors: Hongmei Wang, Zhenzhen Wu, Songtao Lu, Han Zhang, Guoru Ding, Shiyin LiAbstract:In this paper, we investigate deep learning (DL)-enabled signal demodulation methods and establish the first open dataset of real modulated signals for wireless communication systems. Specifically, we propose a flexible communication prototype platform for measuring real modulation dataset. Then, based on the measured dataset, two DL-based Demodulators, called deep belief network (DBN)-support vector machine (SVM) demodulator and adaptive boosting (AdaBoost)-based demodulator, are proposed. The proposed DBN-SVM based demodulator exploits the advantages of both DBN and SVM, i.e., the advantage of DBN as a feature extractor and SVM as a feature classifier. In DBN-SVM based demodulator, the received signals are normalized before being fed to the DBN network. Furthermore, an AdaBoost-based demodulator is developed, which employs the $k$ -nearest neighbor as a weak classifier to form a strong combined classifier. Finally, the experimental results indicate that the proposed DBN-SVM based demodulator and AdaBoost-based demodulator are superior to the single classification method using DBN, SVM, and maximum likelihood-based demodulator.
-
signal demodulation with machine learning methods for physical layer visible light communications prototype platform open dataset and algorithms
IEEE Access, 2019Co-Authors: Songtao Lu, Han Zhang, Hang Li, Chun Du, Shiyin LiAbstract:In this paper, we investigate the design and implementation of machine learning (ML)-based demodulation methods in the physical layer of visible light communication (VLC) systems. We build a flexible hardware prototype of an end-to-end VLC system, from which the received signals are collected as the real data. The dataset is available online, which contains eight types of modulated signals. Then, we propose three ML Demodulators based on convolutional neural network (CNN), the deep belief network (DBN), and adaptive boosting (AdaBoost), respectively. Specifically, the CNN-based demodulator converts the modulated signals to images and recognizes the signals by the image classification. The proposed DBN-based demodulator contains three restricted Boltzmann machines to extract the modulation features. The AdaBoost method includes a strong classifier that is constructed by the weak classifiers with the k -nearest neighbor algorithm. These three Demodulators are trained and tested by our online open dataset. The experimental results show that the demodulation accuracy of the three data-driven Demodulators drops as the transmission distance increases. A higher modulation order negatively influences the accuracy for a given transmission distance. Among the three ML methods, the AdaBoost modulator achieves the best performance.
Mabrouk Kais - One of the best experts on this subject based on the ideXlab platform.
-
Conception et réalisation d'un système de Télécommunications MIMO avec Formation Numérique de Faisceaux en réception ; Calibrage aveugle du Démodulateur triphasé Zéro-IF et comparaison au démodulateur classique à 2 voies I et Q.
HAL CCSD, 2008Co-Authors: Mabrouk KaisAbstract:Within the framework of this research work, we have interested to a MIMO (Multiple Input Multiple Output) telecommunication system using the spatial multiplexing, Zero-IF receptors and the digital beamforming technique. The first part in this work is consecrated to a comparative study between two different kinds of Zero-IF Demodulators: the classical IQ demodulator and the five-port and three-phase one. This study has allowed to highlight the three dimensional aspect of five-port and three-phase Demodulators, to win up to 20dB in terms of rejection of inter-modulation product. Also this three dimensional aspect discovery help us to find a new blind calibration method. The second part of this thesis focuses on the prototyping of a MIMO system. This phase has allowed us to set the difficulties of the implementation of this systems kind and to highlight new problematics that don't appear beforehand in mono-transceiver system. Moreover, a beamforming algorithm was developed in this part. This digital beamfoming has permit to increase the capacity as well as the quality of link when considering the MIMO system as N parallel SIMO systems. Compared to the ZF (Zero Forcing technique), we have proved that the beamforming permit the achievement a better signal quality for lower values of the signal to noise ratio.Dans le cadre de ce travail de recherche, nous nous somme intéressés à un système de télécommunication MIMO (Multiple Input Multiple Output) à multiplexage spatial utilisant des récepteurs Zero-IF et la technique de formation numérique de faisceaux (FF). Le domaine d'application de ces travaux de recherches peuvent être aussi bien les applications fixes (exp: WiFi, IEEE) que les applications mobiles (exp: LTE, 3GPP). La première partie de ce travail est consacrée à une étude comparative entre les différents types de démodulateurs cinq-port et triphasés. Cette étude a permis de mettre en évidence l'aspect tridimensionnel des démodulateurs cinq-port et triphasés, de gagner 20dB en termes de réjection des produits d'intermodulation des signaux adjacents et de trouver une nouvelle méthode de calibrage aveugle du récepteur. La seconde partie de la thèse se concentre sur le prototypage d'un système MIMO. Cette phase nous a permis d'exposer les difficultés de mise en place de ce genre de système et de souligner les nouvelles problématiques qui n'apparaissait pas auparavant dans les systèmes mono- transcepteur. Aussi, un algorithme de Formation de Faisceau a été développé dans cette partie. Ce FF numérique a permis non seulement d'accroître la capacité mais aussi la qualité de liaison en considérant le système MIMO comme N système SIMO en parallèle. Comparativement à la technique ZF(Zero Forcing), nous démontrons que le FF permet d'obtenir une meilleure qualité de signaux pour des faibles valeurs de rapport signal à bruit
-
Conception et réalisation d'un système de télécommunications MIMO avec formation numérique de faisceaux en réception (calibrage aveugle du démodulateur triphasé zéro-IF et comparaison au démodulateur classique à 2 voies I et Q)
2008Co-Authors: Mabrouk Kais, Huyart Bernard, Begaud XavierAbstract:Dans le cadre de ce travail de recherche, nous nous somme intéressés à un système de télécommunication MIMO (Multiple Input Multiple Output) à multiplexage spatial utilisant des récepteurs Zero-IF et la technique de formation numérique de faisceaux (FF). Le domaine d'application de ces travaux de recherches peuvent être aussi bien les applications fixes (exp: WiFi, IEEE) que les applications mobiles (exp: LTE, 3GPP). La première partie de ce travail est consacrée à une étude comparative entre les différents types de démodulateurs cinq-port et triphasés. Cette étude a permis de mettre en évidence l'aspect tridimensionnel des démodulateurs cinq-port et triphasés, de gagner 20dB en termes de réjection des produits d'intermodulation des signaux adjacents et de trouver une nouvelle méthode de calibrage aveugle du récepteur. La seconde partie de la thèse se concentre sur le prototypage d'un système MIMO. Cette phase nous a permis d exposer les difficultés de mise en place de ce genre de système et de souligner les nouvelles problématiques qui n apparaissait pas auparavant dans les systèmes mono- transcepteur. Aussi, un algorithme de Formation de Faisceau a été développé dans cette partie. Ce FF numérique a permis non seulement d'accroître la capacité mais aussi la qualité de liaison en considérant le système MIMO comme N système SIMO en parallèle. Comparativement à la technique ZF(Zero Forcing), nous démontrons que le FF permet d'obtenir une meilleure qualité de signaux pour des faibles valeurs de rapport signal à bruit.Within the framework of this research work, we have interested to a MIMO (Multiple Input Multiple Output) telecommunication system using the spatial multiplexing, Zero-IF receptors and the digital beamforming technique. The first part in this work is consecrated to a comparative study between two different kinds of Zero-IF Demodulators: the classical IQ demodulator and the five-port and three-phase one. This study has allowed to highlight the three dimensional aspect of five-port and three-phase Demodulators, to win up to 20dB in terms of rejection of inter-modulation product. Also this three dimensional aspect discovery help us to find a new blind calibration method. The second part of this thesis focuses on the prototyping of a MIMO system. This phase has allowed us to set the difficulties of the implementation of this systems kind and to highlight new problematics that don t appear beforehand in mono-transceiver system. Moreover, a beamforming algorithm was developed in this part. This digital beamfoming has permit to increase the capacity as well as the quality of link when considering the MIMO system as N parallel SIMO systems. Compared to the ZF (Zero Forcing technique), we have proved that the beamforming permit the achievement a better signal quality for lower values of the signal to noise ratio.PARIS-Télécom ParisTech (751132302) / SudocSudocFranceF