Kang Xiao-Fei
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Kang Xiao-Fei has a total of 10 co-authors. Here are the top co-authors by number of shared publications:
Li Bai-Ping
Coll. of Commun. & Inf. Eng., Xi'an Univ. of Sci. & Technol., Xi'an, China
2 shared publicationsJia-Wei Yang
State Key Laboratory of Integrated Service Networks, Xidian University, Xi'an 710071, China
1 shared publication- Meng Yao
Affiliation College of Communication and Information Engineering, Xi’an University of Science and Technology, Xi’an 710054, China
1 shared publication Mengmeng Li
Xi’an University of Science and Technology,College of Communication and Information Engineering,Xi’an,China,710054
1 shared publication- Qiyue Liang
College of Communication and Information Engineering, Xi’an University of Science and Technology, Xi’an 710054, China
1 shared publication Shuo Men
College of Electronic Information and Automation, Chongqing University of Technology, Chongqing 400054, China
1 shared publication
Latest Publications
- Open Access
Indoor Localization Algorithm Based on a High-Order Graph Neural Network
Given that fingerprint localization methods can be effectively modeled as supervised learning problems, machine learning has been employed for indoor localization tasks based on fingerprint methods. However, it is often challenging for popular machine learning models to effectively capture the unstructured data features inherent in fingerprint data that are generated in diverse propagation environments. In this paper, we propose an indoor localization algorithm based on a high-order graph neural network (HoGNNLoc) to enhance the accuracy of indoor localization and improve localization stability in dynamic environments. The algorithm first designs an adjacency matrix based on the spatial relative locations of access points (APs) to obtain a graph structure; on this basis, a high-order graph neural network is constructed to extract and aggregate the features; finally, the designed fully connected network is used to achieve the regression prediction of the location of the target to be located. The experimental results on our self-built dataset show that the proposed algorithm achieves localization accuracy within 1.29 m at 80% of the cumulative distribution function (CDF) points. The improvements are 59.2%, 51.3%, 36.1%, and 22.7% compared to the K-nearest neighbors (KNN), deep neural network (DNN), simple graph convolutional network (SGC), and graph attention network (GAT). Moreover, even with a 30% reduction in fingerprint data, the proposed algorithm exhibits stable localization performance. On a public dataset, our proposed localization algorithm can also show better performance.
Open AccessIndoor Localization Algorithm Based on a High-Order Graph Neural Network
Given that fingerprint localization methods can be effectively modeled as supervised learning problems, machine learning has been employed for indoor localization tasks based on fingerprint methods. However, it is often challenging for popular machine learning models to effectively capture the unstructured data features inherent in fingerprint data that are generated in diverse propagation environments. In this paper, we propose an indoor localization algorithm based on a high-order graph neural network (HoGNNLoc) to enhance the accuracy of indoor localization and improve localization stability in dynamic environments. The algorithm first designs an adjacency matrix based on the spatial relative locations of access points (APs) to obtain a graph structure; on this basis, a high-order graph neural network is constructed to extract and aggregate the features; finally, the designed fully connected network is used to achieve the regression prediction of the location of the target to be located. The experimental results on our self-built dataset show that the proposed algorithm achieves localization accuracy within 1.29 m at 80% of the cumulative distribution function (CDF) points. The improvements are 59.2%, 51.3%, 36.1%, and 22.7% compared to the K-nearest neighbors (KNN), deep neural network (DNN), simple graph convolutional network (SGC), and graph attention network (GAT). Moreover, even with a 30% reduction in fingerprint data, the proposed algorithm exhibits stable localization performance. On a public dataset, our proposed localization algorithm can also show better performance.
- Open Access
Deep Learning for Joint Pilot Design and Channel Estimation in MIMO-OFDM Systems
In MIMO-OFDM systems, pilot design and estimation algorithm jointly determine the reliability and effectiveness of pilot-based channel estimation methods. In order to improve the channel estimation accuracy with less pilot overhead, a deep learning scheme for joint pilot design and channel estimation is proposed. This new hybrid network structure is named CAGAN, which is composed of a concrete autoencoder (concrete AE) and a conditional generative adversarial network (cGAN). We first use concrete AE to find and select the most informative position in the time-frequency grid to achieve pilot optimization design and then input the optimized pilots to cGAN to complete channel estimation. Simulation experiments show that the CAGAN scheme outperforms the traditional LS and MMSE estimation methods with fewer pilots, and has good robustness to environmental noise.
Open AccessDeep Learning for Joint Pilot Design and Channel Estimation in MIMO-OFDM Systems
In MIMO-OFDM systems, pilot design and estimation algorithm jointly determine the reliability and effectiveness of pilot-based channel estimation methods. In order to improve the channel estimation accuracy with less pilot overhead, a deep learning scheme for joint pilot design and channel estimation is proposed. This new hybrid network structure is named CAGAN, which is composed of a concrete autoencoder (concrete AE) and a conditional generative adversarial network (cGAN). We first use concrete AE to find and select the most informative position in the time-frequency grid to achieve pilot optimization design and then input the optimized pilots to cGAN to complete channel estimation. Simulation experiments show that the CAGAN scheme outperforms the traditional LS and MMSE estimation methods with fewer pilots, and has good robustness to environmental noise.
- 1 October 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 456-460
Performance Comparison and Evaluation of Indoor Positioning Technology Based on Machine Learning Algorithms
Precise location of things in indoor environments is the essential information for future wireless networks and services. Wi-Fi fingerprinting positioning has recently attracted great attention due to its high applicability in the complex indoor environments, although it still needs to improve positioning accuracy. In this paper, we introduce machine learning algorithms combined with filtering techniques to improve positioning accuracy. We compare and evaluate several positioning accuracies based on machine learning algorithms. The experimental results show that the performance of the GBDT algorithm is better than that of KNN, SVM and RF, and the performance of the regression method is better than the classification method for the same machine learning algorithm. In addition, we introduce filtering methods in the online phase. The simulation results indicate that the Kalman filtering method can further improve the positioning accuracy.
- 1 October 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 456-460
Performance Comparison and Evaluation of Indoor Positioning Technology Based on Machine Learning Algorithms
Precise location of things in indoor environments is the essential information for future wireless networks and services. Wi-Fi fingerprinting positioning has recently attracted great attention due to its high applicability in the complex indoor environments, although it still needs to improve positioning accuracy. In this paper, we introduce machine learning algorithms combined with filtering techniques to improve positioning accuracy. We compare and evaluate several positioning accuracies based on machine learning algorithms. The experimental results show that the performance of the GBDT algorithm is better than that of KNN, SVM and RF, and the performance of the regression method is better than the classification method for the same machine learning algorithm. In addition, we introduce filtering methods in the online phase. The simulation results indicate that the Kalman filtering method can further improve the positioning accuracy.
- 18 August 2016
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 136-139
A Rake-MMSE Receiver Based on RLS Algorithm for UWB Systems
A novel adaptive Rake-MMSE receiver for DS-UWB systems in the presence of both multi-path interference and narrowband interference is proposed. The receiver firstly adopts Rake reception to separate and extract multi-path components, and then uses MMSE method to combine multi-path components for eliminating narrowband interference. In combining schemes, an adaptive RLS algorithm is adopted to reduce the complexity. The simulation results based on the IEEE 802.15.3a channel models (CM1 to CM4) show that the proposed receiver has reasonably good BER performance and faster convergence rate.
- 18 August 2016
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 136-139
A Rake-MMSE Receiver Based on RLS Algorithm for UWB Systems
A novel adaptive Rake-MMSE receiver for DS-UWB systems in the presence of both multi-path interference and narrowband interference is proposed. The receiver firstly adopts Rake reception to separate and extract multi-path components, and then uses MMSE method to combine multi-path components for eliminating narrowband interference. In combining schemes, an adaptive RLS algorithm is adopted to reduce the complexity. The simulation results based on the IEEE 802.15.3a channel models (CM1 to CM4) show that the proposed receiver has reasonably good BER performance and faster convergence rate.
- 1 September 2014
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 52, 267-269
The BER performance analysis and simulation of rake receiver for UWB systems
Inter symbol interference (ISI) due to the dense multi-path nature of the UWB channel results in large performance degradation, the Rake receiver can effectively overcome the ISI problems, in this paper, the analytical BER expression for the UWB system using the Rake receiver in the multi-path channel is derived. Furthermore, the performance of A-Rake, P-Rake and S-Rake is evaluated for TH-UWB system and DS-UWB system. Finally, based on the simulation results, conclusions are drawn considering the performance and complexity issues for system design in the IEEE 802.15.3a UWB channel.
- 1 September 2014
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 52, 267-269
The BER performance analysis and simulation of rake receiver for UWB systems
Inter symbol interference (ISI) due to the dense multi-path nature of the UWB channel results in large performance degradation, the Rake receiver can effectively overcome the ISI problems, in this paper, the analytical BER expression for the UWB system using the Rake receiver in the multi-path channel is derived. Furthermore, the performance of A-Rake, P-Rake and S-Rake is evaluated for TH-UWB system and DS-UWB system. Finally, based on the simulation results, conclusions are drawn considering the performance and complexity issues for system design in the IEEE 802.15.3a UWB channel.
- 31 December 2011
- Published by Elsevier in The Journal of China Universities of Posts and Telecommunications
- Vol. 18 (6) , 38-43
Blind adaptive receiver based on RLS-CMA for TH-UWB system
- 31 December 2011
- Published by Elsevier in The Journal of China Universities of Posts and Telecommunications
- Vol. 18 (6) , 38-43
Blind adaptive receiver based on RLS-CMA for TH-UWB system