Xudong Song
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
Research Subjects
Xudong Song has a total of 22 co-authors. Here are the top co-authors by number of shared publications:
- Xiaochen Fan
Institute for Electronics and Information Technology in Tianjin, Tsinghua University
4 shared publications - Gengfa Fang
University of Technology Sydney
2 shared publications - Hongxia Bie
Intelligent Media Computing Center, School of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijing 100876, China
2 shared publications - Qianwen Ye
School of Information and Communication Engineering, Beijing University of Posts and Telecommunications, Beijing, China
2 shared publications - Chao Chen
College of Computer Science, Chongqing University, Chongqing, China
1 shared publication Chaocan Xiang
College of Computer Science, Chongqing University, Chongqing, China
1 shared publication
Latest Publications
- 23 May 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Network Science and Engineering
- Vol. 10 (5) , 2964-2977
SE-Loc: Security-Enhanced Indoor Localization With Semi-Supervised Deep Learning
Wireless indoor localization has become unavoidable for industrial indoor location-based services. Given the ubiquitous deployment of wireless access points (APs), WiFi fingerprinting of Received Signal Strength (RSS) has been widely adopted for indoor localization. Meanwhile, existing RSS fingerprint-based methods lack security-oriented considerations and are vulnerable to malicious attacks. When security vulnerabilities are exploited, mobile users may confront indoor localization mismatches, faults and even localization system failures. In this paper, we propose SE-Loc, a semi-supervised learning-based technique to enhance security and resiliency of fingerprint-based localization. The architecture of SE-Loc consists of two parts: (1) a correlation-based AP selection for processing RSS fingerprints and fingerprint-image generation, and (2) a deep learning model based on a denoising autoencoder and convolutional neural networks for robust feature learning and location matching. Extensive experiments show that under potential AP attacks, SE-Loc demonstrates superior performance on indoor localization over the state-of-the-art methods. With up to 100 malicious attacking APs in the UJIIndoorLoc edge server, SE-Loc can still achieve the lowest error fluctuation of 1.7 m and the highest average localization accuracy of 8.9 m.
- 23 May 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Network Science and Engineering
- Vol. 10 (5) , 2964-2977
SE-Loc: Security-Enhanced Indoor Localization With Semi-Supervised Deep Learning
Wireless indoor localization has become unavoidable for industrial indoor location-based services. Given the ubiquitous deployment of wireless access points (APs), WiFi fingerprinting of Received Signal Strength (RSS) has been widely adopted for indoor localization. Meanwhile, existing RSS fingerprint-based methods lack security-oriented considerations and are vulnerable to malicious attacks. When security vulnerabilities are exploited, mobile users may confront indoor localization mismatches, faults and even localization system failures. In this paper, we propose SE-Loc, a semi-supervised learning-based technique to enhance security and resiliency of fingerprint-based localization. The architecture of SE-Loc consists of two parts: (1) a correlation-based AP selection for processing RSS fingerprints and fingerprint-image generation, and (2) a deep learning model based on a denoising autoencoder and convolutional neural networks for robust feature learning and location matching. Extensive experiments show that under potential AP attacks, SE-Loc demonstrates superior performance on indoor localization over the state-of-the-art methods. With up to 100 malicious attacking APs in the UJIIndoorLoc edge server, SE-Loc can still achieve the lowest error fluctuation of 1.7 m and the highest average localization accuracy of 8.9 m.
- 1 June 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-6
CapsLoc: A Robust Indoor Localization System with WiFi Fingerprinting Using Capsule Networks
With the unprecedented demand of location-based services in indoor scenarios, wireless indoor localization is emerging as an essential application for mobile users. While the line-of-sight GPS signal is not available at indoor spaces, WiFi fingerprinting using received signal strength (RSS) has become popular with its ubiquitous accessibility. Although the fingerprinting data can be easily collected by portable mobile devices, to achieve robust and efficient indoor localization remains challenging with two constraints. First, the localization accuracy will be degraded by the random fluctuation of signals that caused by multipath effects from RSS signals. Second, indoor localization algorithms are time-consuming due to the handcrafting features and complex filtering on raw dataset. To achieve high localization accuracy with WiFi fingerprinting, in this paper, we propose CapsLoc, a robust indoor localization system by using capsule networks. Specifically, the capsule network model can efficiently extract hierarchical structures from WiFi fingerprint with three main components, including a convolutional layer, a primary capsule layer and a feature capsule layer. We conduct a real-world experimental field test with over 33600 data points. The experimental results show that CapsLoc can achieve accurate indoor localization with an averaged error of 0.68 m, which outperforms conventional machine learning methods (KNN and SVM) and existing deep learning methods (CNN and SAE-CNN).
- 1 June 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-6
CapsLoc: A Robust Indoor Localization System with WiFi Fingerprinting Using Capsule Networks
With the unprecedented demand of location-based services in indoor scenarios, wireless indoor localization is emerging as an essential application for mobile users. While the line-of-sight GPS signal is not available at indoor spaces, WiFi fingerprinting using received signal strength (RSS) has become popular with its ubiquitous accessibility. Although the fingerprinting data can be easily collected by portable mobile devices, to achieve robust and efficient indoor localization remains challenging with two constraints. First, the localization accuracy will be degraded by the random fluctuation of signals that caused by multipath effects from RSS signals. Second, indoor localization algorithms are time-consuming due to the handcrafting features and complex filtering on raw dataset. To achieve high localization accuracy with WiFi fingerprinting, in this paper, we propose CapsLoc, a robust indoor localization system by using capsule networks. Specifically, the capsule network model can efficiently extract hierarchical structures from WiFi fingerprint with three main components, including a convolutional layer, a primary capsule layer and a feature capsule layer. We conduct a real-world experimental field test with over 33600 data points. The experimental results show that CapsLoc can achieve accurate indoor localization with an averaged error of 0.68 m, which outperforms conventional machine learning methods (KNN and SVM) and existing deep learning methods (CNN and SAE-CNN).
- 28 February 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Mobile Computing
- Vol. 20 (6) , 2154-2171
BuildSenSys: Reusing Building Sensing Data for Traffic Prediction With Cross-Domain Learning
With the rapid development of smart cities, smart buildings are generating a massive amount of building sensing data by the equipped sensors. Indeed, building sensing data provides a promising way to enrich a series of data-demanding and cost-expensive urban mobile applications. In this paper, as a preliminary exploration, we study how to reuse building sensing data to predict traffic volume on nearby roads. Compared with existing studies, reusing building sensing data has considerable merits of cost-efficiency and high-reliability. Nevertheless, it is non-trivial to achieve accurate prediction on such cross-domain data with two major challenges. First, relationships between building sensing data and traffic data are not unknown as prior, and the spatio-temporal complexities impose more difficulties to uncover the underlying reasons behind the above relationships. Second, it is even more daunting to accurately predict traffic volume with dynamic building-traffic correlations, which are cross-domain, non-linear, and time-varying. To address the above challenges, we design and implement BuildSenSys , a first-of-its-kind system for nearby traffic volume prediction by reusing building sensing data. Our work consists of two parts, i.e., Correlation Analysis and Cross-domain Learning . First, we conduct a comprehensive building-traffic analysis based on multi-source datasets, disclosing how and why building sensing data is correlated with nearby traffic volume. Second, we propose a novel recurrent neural network for traffic volume prediction based on cross-domain learning with two attention mechanisms. Specifically, a cross-domain attention mechanism captures the building-traffic correlations and adaptively extracts the most relevant building sensing data at each predicting step. Then, a temporal attention mechanism is employed to model the temporal dependencies of data across historical time intervals. The extensive experimental studies demonstrate that BuildSenSys outperforms all baseline methods with up to 65.3 percent accuracy improvement (e.g., 2.2 percent MAPE) in predicting nearby traffic volume. We believe that this work can open a new gate of reusing building sensing data for urban traffic sensing, thus establishing connections between smart buildings and intelligent transportation.
- 28 February 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Mobile Computing
- Vol. 20 (6) , 2154-2171
BuildSenSys: Reusing Building Sensing Data for Traffic Prediction With Cross-Domain Learning
With the rapid development of smart cities, smart buildings are generating a massive amount of building sensing data by the equipped sensors. Indeed, building sensing data provides a promising way to enrich a series of data-demanding and cost-expensive urban mobile applications. In this paper, as a preliminary exploration, we study how to reuse building sensing data to predict traffic volume on nearby roads. Compared with existing studies, reusing building sensing data has considerable merits of cost-efficiency and high-reliability. Nevertheless, it is non-trivial to achieve accurate prediction on such cross-domain data with two major challenges. First, relationships between building sensing data and traffic data are not unknown as prior, and the spatio-temporal complexities impose more difficulties to uncover the underlying reasons behind the above relationships. Second, it is even more daunting to accurately predict traffic volume with dynamic building-traffic correlations, which are cross-domain, non-linear, and time-varying. To address the above challenges, we design and implement BuildSenSys , a first-of-its-kind system for nearby traffic volume prediction by reusing building sensing data. Our work consists of two parts, i.e., Correlation Analysis and Cross-domain Learning . First, we conduct a comprehensive building-traffic analysis based on multi-source datasets, disclosing how and why building sensing data is correlated with nearby traffic volume. Second, we propose a novel recurrent neural network for traffic volume prediction based on cross-domain learning with two attention mechanisms. Specifically, a cross-domain attention mechanism captures the building-traffic correlations and adaptively extracts the most relevant building sensing data at each predicting step. Then, a temporal attention mechanism is employed to model the temporal dependencies of data across historical time intervals. The extensive experimental studies demonstrate that BuildSenSys outperforms all baseline methods with up to 65.3 percent accuracy improvement (e.g., 2.2 percent MAPE) in predicting nearby traffic volume. We believe that this work can open a new gate of reusing building sensing data for urban traffic sensing, thus establishing connections between smart buildings and intelligent transportation.
- Top Cited PapersOpen Access
- 8 August 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 7, 110698-110709
A Novel Convolutional Neural Network Based Indoor Localization Framework With WiFi Fingerprinting
With the ubiquitous deployment of wireless systems and pervasive availability of smart devices, indoor localization is empowering numerous location-based services. With the established radio maps, WiFi fingerprinting has become one of the most practical approaches to localize mobile users. However, most fingerprint-based localization algorithms are computation-intensive, with heavy dependence on both offline training phase and online localization phase. In this paper, we propose CNNLoc, a Convolutional Neural Network (CNN) based indoor localization system with WiFi fingerprints for multi-building and multi-floor localization. Specifically, we devise a novel classification model and a novel positioning model by combining a Stacked Auto-Encoder (SAE) with a one-dimensional CNN. The SAE is utilized to precisely extract key features from sparse Received Signal Strength (RSS) data while the CNN is trained to effectively achieve high accuracy in the positioning phase. We evaluate the proposed system on the UJIIndoorLoc dataset and Tampere dataset and compare the performance with several state-of-the-art methods. Moreover, we further propose a newly collected WiFi fingerprinting dataset UTSIndoorLoc and test the positioning model of CNNLoc on it. The results show CNNLoc outperforms the existing solutions with 100% and 95% success rates on building-level localization and floor-level localization, respectively.
- 8 August 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 7, 110698-110709
Top Cited PapersOpen AccessA Novel Convolutional Neural Network Based Indoor Localization Framework With WiFi Fingerprinting
With the ubiquitous deployment of wireless systems and pervasive availability of smart devices, indoor localization is empowering numerous location-based services. With the established radio maps, WiFi fingerprinting has become one of the most practical approaches to localize mobile users. However, most fingerprint-based localization algorithms are computation-intensive, with heavy dependence on both offline training phase and online localization phase. In this paper, we propose CNNLoc, a Convolutional Neural Network (CNN) based indoor localization system with WiFi fingerprints for multi-building and multi-floor localization. Specifically, we devise a novel classification model and a novel positioning model by combining a Stacked Auto-Encoder (SAE) with a one-dimensional CNN. The SAE is utilized to precisely extract key features from sparse Received Signal Strength (RSS) data while the CNN is trained to effectively achieve high accuracy in the positioning phase. We evaluate the proposed system on the UJIIndoorLoc dataset and Tampere dataset and compare the performance with several state-of-the-art methods. Moreover, we further propose a newly collected WiFi fingerprinting dataset UTSIndoorLoc and test the positioning model of CNNLoc on it. The results show CNNLoc outperforms the existing solutions with 100% and 95% success rates on building-level localization and floor-level localization, respectively.
- 1 May 2009
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 27 (5) , 11-18
A Workflow Framework for Intelligent Service Composition
Generally, service composition and its evaluation are initiated by web services' functional and non-functional attributes. To select qualified services and compose them into a service composition framework manually is time-consuming and error-prone. In practice, it is a challenging endeavor to timely discover qualified services and develop a service composition schema. In view of this challenge, a workflow framework is presented in this paper for intelligently navigating service composition. The workflow framework consists of two primary processing modules: planning module and CSP (constraint satisfaction problems) solving module. Planning module aims at producing composite plans taking advantage of services' functional attributes. Moreover, CSP solving module aims at selecting an appropriate service, taking advantaging of services' non-functional attributes, from a group of qualified services that own the same functionality. This group of qualified services is instantiated from a service class predefined. Finally, a case study is presented to demonstrate the framework.
- 1 May 2009
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 27 (5) , 11-18
A Workflow Framework for Intelligent Service Composition
Generally, service composition and its evaluation are initiated by web services' functional and non-functional attributes. To select qualified services and compose them into a service composition framework manually is time-consuming and error-prone. In practice, it is a challenging endeavor to timely discover qualified services and develop a service composition schema. In view of this challenge, a workflow framework is presented in this paper for intelligently navigating service composition. The workflow framework consists of two primary processing modules: planning module and CSP (constraint satisfaction problems) solving module. Planning module aims at producing composite plans taking advantage of services' functional attributes. Moreover, CSP solving module aims at selecting an appropriate service, taking advantaging of services' non-functional attributes, from a group of qualified services that own the same functionality. This group of qualified services is instantiated from a service class predefined. Finally, a case study is presented to demonstrate the framework.