A federated learning-based license plate recognition scheme for 5G-enabled Internet of vehicles
- Kong, Xiangjie, Wang, Kailai, Hou, Mingliang, Hao, Xinyu, Shen, Guojiang, Chen, Xin, Xia, Feng
- Authors: Kong, Xiangjie , Wang, Kailai , Hou, Mingliang , Hao, Xinyu , Shen, Guojiang , Chen, Xin , Xia, Feng
- Date: 2021
- Type: Text , Journal article
- Relation: IEEE Transactions on Industrial Informatics Vol. 17, no. 12 (Dec 2021), p. 8523-8530
- Full Text:
- Reviewed:
- Description: License plate is an essential characteristic to identify vehicles for the traffic management, and thus, license plate recognition is important for Internet of Vehicles. Since 5G has been widely covered, mobile devices are utilized to assist the traffic management, which is a significant part of Industry 4.0. However, there have always been privacy risks due to centralized training of models. Also, the trained model cannot be directly deployed on the mobile device due to its large number of parameters. In this article, we propose a federated learning-based license plate recognition framework (FedLPR) to solve these problems. We design detection and recognition model to apply in the mobile device. In terms of user privacy, data in individuals is harnessed on their mobile devices instead of the server to train models based on federated learning. Extensive experiments demonstrate that FedLPR has high accuracy and acceptable communication cost while preserving user privacy.
- Authors: Kong, Xiangjie , Wang, Kailai , Hou, Mingliang , Hao, Xinyu , Shen, Guojiang , Chen, Xin , Xia, Feng
- Date: 2021
- Type: Text , Journal article
- Relation: IEEE Transactions on Industrial Informatics Vol. 17, no. 12 (Dec 2021), p. 8523-8530
- Full Text:
- Reviewed:
- Description: License plate is an essential characteristic to identify vehicles for the traffic management, and thus, license plate recognition is important for Internet of Vehicles. Since 5G has been widely covered, mobile devices are utilized to assist the traffic management, which is a significant part of Industry 4.0. However, there have always been privacy risks due to centralized training of models. Also, the trained model cannot be directly deployed on the mobile device due to its large number of parameters. In this article, we propose a federated learning-based license plate recognition framework (FedLPR) to solve these problems. We design detection and recognition model to apply in the mobile device. In terms of user privacy, data in individuals is harnessed on their mobile devices instead of the server to train models based on federated learning. Extensive experiments demonstrate that FedLPR has high accuracy and acceptable communication cost while preserving user privacy.
A shared bus profiling scheme for smart cities based on heterogeneous mobile crowdsourced data
- Kong, Xiangjie, Xia, Feng, Li, Jianxin, Hou, Mingliang, Li, Menglin, Xiang, Yong
- Authors: Kong, Xiangjie , Xia, Feng , Li, Jianxin , Hou, Mingliang , Li, Menglin , Xiang, Yong
- Date: 2020
- Type: Text , Journal article
- Relation: IEEE Transactions on Industrial Informatics Vol. 16, no. 2 (2020), p. 1436-1444
- Full Text:
- Reviewed:
- Description: Mobile crowdsourcing (MCS), as an effective and crucial technique of Industrial Internet of Things, is enabling smart city initiatives in the real world. It aims at incorporating the intelligence of dynamic crowds to collect and compute decentralized ubiquitous sensing data that can be used to solve major urbanization problems such as traffic congestion. The shared bus, as a neotype transportation mode, aims at improving the resource utilization rate and maintaining the advantages of convenience and economy. In this article, we provide a scheme to profile shared buses through heterogeneous mobile crowdsourced data (TRProfiling). First, we design an MCS-based shared bus data generation and collection solution to overcome the aforementioned data scarcity issue. Then, we propose a travel profiling to profile resident travel and design a method called multiconstraint evolution algorithm to optimize the routes. Experimental results demonstrate that TRProfiling has an excellent performance in satisfying passengers' travel requirements. © 2005-2012 IEEE.
- Authors: Kong, Xiangjie , Xia, Feng , Li, Jianxin , Hou, Mingliang , Li, Menglin , Xiang, Yong
- Date: 2020
- Type: Text , Journal article
- Relation: IEEE Transactions on Industrial Informatics Vol. 16, no. 2 (2020), p. 1436-1444
- Full Text:
- Reviewed:
- Description: Mobile crowdsourcing (MCS), as an effective and crucial technique of Industrial Internet of Things, is enabling smart city initiatives in the real world. It aims at incorporating the intelligence of dynamic crowds to collect and compute decentralized ubiquitous sensing data that can be used to solve major urbanization problems such as traffic congestion. The shared bus, as a neotype transportation mode, aims at improving the resource utilization rate and maintaining the advantages of convenience and economy. In this article, we provide a scheme to profile shared buses through heterogeneous mobile crowdsourced data (TRProfiling). First, we design an MCS-based shared bus data generation and collection solution to overcome the aforementioned data scarcity issue. Then, we propose a travel profiling to profile resident travel and design a method called multiconstraint evolution algorithm to optimize the routes. Experimental results demonstrate that TRProfiling has an excellent performance in satisfying passengers' travel requirements. © 2005-2012 IEEE.
A3Graph : adversarial attributed autoencoder for graph representation learning
- Hou, Mingliang, Wang, Lei, Liu, Jiaying, Kong, Xiangjie, Xia, Feng
- Authors: Hou, Mingliang , Wang, Lei , Liu, Jiaying , Kong, Xiangjie , Xia, Feng
- Date: 2021
- Type: Text , Conference paper
- Relation: 36th Annual ACM Symposium on Applied Computing, SAC 2021 p. 1697-1704
- Full Text:
- Reviewed:
- Description: Recent years have witnessed a proliferation of graph representation techniques in social network analysis. Graph representation aims to map nodes in the graph into low-dimensional vector space while preserving as much information as possible. However, most existing methods ignore the robustness of learned latent vectors, which leads to inferior representation results due to sparse and noisy data in graphs. In this paper, we propose a novel framework, named A3Graph, which aims to improve the robustness and stability of graph representations. Specifically, we first construct an aggregation matrix by the combining positive point-wise mutual information matrix with the attribute matrix. Then, we enforce the autoencoder to reconstruct the aggregation matrix instead of the input attribute matrix. The enhancement autoencoder can incorporate structural and attributed information in a joint learning way to improve the noise-resilient during the learning process. Furthermore, an adversarial learning component is leveraged in our framework to impose a prior distribution on learned representations has been demonstrated as an effective mechanism in improving the robustness and stability in representation learning. Experimental studies on real-world datasets have demonstrated the effectiveness of the proposed A3Graph. © 2021 ACM.
- Authors: Hou, Mingliang , Wang, Lei , Liu, Jiaying , Kong, Xiangjie , Xia, Feng
- Date: 2021
- Type: Text , Conference paper
- Relation: 36th Annual ACM Symposium on Applied Computing, SAC 2021 p. 1697-1704
- Full Text:
- Reviewed:
- Description: Recent years have witnessed a proliferation of graph representation techniques in social network analysis. Graph representation aims to map nodes in the graph into low-dimensional vector space while preserving as much information as possible. However, most existing methods ignore the robustness of learned latent vectors, which leads to inferior representation results due to sparse and noisy data in graphs. In this paper, we propose a novel framework, named A3Graph, which aims to improve the robustness and stability of graph representations. Specifically, we first construct an aggregation matrix by the combining positive point-wise mutual information matrix with the attribute matrix. Then, we enforce the autoencoder to reconstruct the aggregation matrix instead of the input attribute matrix. The enhancement autoencoder can incorporate structural and attributed information in a joint learning way to improve the noise-resilient during the learning process. Furthermore, an adversarial learning component is leveraged in our framework to impose a prior distribution on learned representations has been demonstrated as an effective mechanism in improving the robustness and stability in representation learning. Experimental studies on real-world datasets have demonstrated the effectiveness of the proposed A3Graph. © 2021 ACM.
API : an index for quantifying a scholar's academic potential
- Ren, Jing, Wang, Lei, Wang, Kailai, Yu, Shuo, Hou, Mingliang, Lee, Ivan, Kong, Xiangje, Xia, Feng
- Authors: Ren, Jing , Wang, Lei , Wang, Kailai , Yu, Shuo , Hou, Mingliang , Lee, Ivan , Kong, Xiangje , Xia, Feng
- Date: 2019
- Type: Text , Journal article
- Relation: IEEE Access Vol. 7, no. (2019), p. 178675-178684
- Full Text:
- Reviewed:
- Description: In the context of big scholarly data, various metrics and indicators have been widely applied to evaluate the impact of scholars from different perspectives, such as publication counts, citations, ${h}$-index, and their variants. However, these indicators have limited capacity in characterizing prospective impacts or achievements of scholars. To solve this problem, we propose the Academic Potential Index (API) to quantify scholar's academic potential. Furthermore, an algorithm is devised to calculate the value of API. It should be noted that API is a dynamic index throughout scholar's academic career. By applying API to rank scholars, we can identify scholars who show their academic potentials during the early academic careers. With extensive experiments conducted based on the Microsoft Academic Graph dataset, it can be found that the proposed index evaluates scholars' academic potentials effectively and captures the variation tendency of their academic impacts. Besides, we also apply this index to identify rising stars in academia. Experimental results show that the proposed API can achieve superior performance in identifying potential scholars compared with three baseline methods. © 2019 IEEE.
- Authors: Ren, Jing , Wang, Lei , Wang, Kailai , Yu, Shuo , Hou, Mingliang , Lee, Ivan , Kong, Xiangje , Xia, Feng
- Date: 2019
- Type: Text , Journal article
- Relation: IEEE Access Vol. 7, no. (2019), p. 178675-178684
- Full Text:
- Reviewed:
- Description: In the context of big scholarly data, various metrics and indicators have been widely applied to evaluate the impact of scholars from different perspectives, such as publication counts, citations, ${h}$-index, and their variants. However, these indicators have limited capacity in characterizing prospective impacts or achievements of scholars. To solve this problem, we propose the Academic Potential Index (API) to quantify scholar's academic potential. Furthermore, an algorithm is devised to calculate the value of API. It should be noted that API is a dynamic index throughout scholar's academic career. By applying API to rank scholars, we can identify scholars who show their academic potentials during the early academic careers. With extensive experiments conducted based on the Microsoft Academic Graph dataset, it can be found that the proposed index evaluates scholars' academic potentials effectively and captures the variation tendency of their academic impacts. Besides, we also apply this index to identify rising stars in academia. Experimental results show that the proposed API can achieve superior performance in identifying potential scholars compared with three baseline methods. © 2019 IEEE.
Cross network representation matching with outliers
- Hou, Mingliang, Ren, Jing, Febrinanto, Febrinanto, Shehzad, Ahsan, Xia, Feng
- Authors: Hou, Mingliang , Ren, Jing , Febrinanto, Febrinanto , Shehzad, Ahsan , Xia, Feng
- Date: 2021
- Type: Text , Conference paper
- Relation: 21st IEEE International Conference on Data Mining Workshops, ICDMW 2021, Virtual, online, 7-10 December 2021, IEEE International Conference on Data Mining Workshops, ICDMW Vol. 2021-December, p. 951-958
- Full Text:
- Reviewed:
- Description: Research has revealed the effectiveness of network representation techniques in handling diverse downstream machine learning tasks upon graph structured data. However, most network representation methods only seek to learn information in a single network, which fails to learn knowledge across different networks. Moreover, outliers in real-world networks pose great challenges to match distribution shift of learned embeddings. In this paper, we propose a novel joint learning framework, called CrossOSR, to learn network-invariant embeddings across different networks in the presence of outliers in the source network. To learn outlier-aware representations, a modified graph convolutional network (GCN) layer is designed to indicate the potential outliers. To learn more fine-grained information between different domains, a subdomain matching is adopted to align the shift distribution of learned vectors. To learn robust network representations, the learned indicator is utilized to smooth the noise effect from source domain to target domain. Extensive experimental results on three real-world datasets in the node classification task show that the proposed framework yields state-of-the-art cross network representation matching performance with outliers in the source network. © 2021 IEEE.
- Authors: Hou, Mingliang , Ren, Jing , Febrinanto, Febrinanto , Shehzad, Ahsan , Xia, Feng
- Date: 2021
- Type: Text , Conference paper
- Relation: 21st IEEE International Conference on Data Mining Workshops, ICDMW 2021, Virtual, online, 7-10 December 2021, IEEE International Conference on Data Mining Workshops, ICDMW Vol. 2021-December, p. 951-958
- Full Text:
- Reviewed:
- Description: Research has revealed the effectiveness of network representation techniques in handling diverse downstream machine learning tasks upon graph structured data. However, most network representation methods only seek to learn information in a single network, which fails to learn knowledge across different networks. Moreover, outliers in real-world networks pose great challenges to match distribution shift of learned embeddings. In this paper, we propose a novel joint learning framework, called CrossOSR, to learn network-invariant embeddings across different networks in the presence of outliers in the source network. To learn outlier-aware representations, a modified graph convolutional network (GCN) layer is designed to indicate the potential outliers. To learn more fine-grained information between different domains, a subdomain matching is adopted to align the shift distribution of learned vectors. To learn robust network representations, the learned indicator is utilized to smooth the noise effect from source domain to target domain. Extensive experimental results on three real-world datasets in the node classification task show that the proposed framework yields state-of-the-art cross network representation matching performance with outliers in the source network. © 2021 IEEE.
Decision behavior based private vehicle trajectory generation towards smart cities
- Chen, Qiao, Ma, Kai, Hou, Mingliang, Kong, Xiangjie, Xia, Feng
- Authors: Chen, Qiao , Ma, Kai , Hou, Mingliang , Kong, Xiangjie , Xia, Feng
- Date: 2021
- Type: Text , Conference paper
- Relation: 18th International Conference on Web Information Systems and Applications, WISA 2021 Vol. 12999 LNCS, p. 109-120
- Full Text:
- Reviewed:
- Description: In contrast with the condition that the trajectory dataset of floating cars (taxis) can be easily obtained from the Internet, it is hard to get the trajectory data of social vehicles (private vehicles) because of personal privacy and government policies. This paper absorbs the idea of game theory, considers the influence of individuals in the group, and proposes a decision behavior based dataset generation (DBDG) model of vehicles to predict future inter-regional traffic. In addition, we adopt simulation tools and generative adversarial networks to train the trajectory prediction model so that the private vehicle trajectory dataset conforming to social rules (e.g., collisionless) is generated. Finally, we construct from macroscopic and microscopic perspectives to verify dataset generation methods proposed in this paper. The results show that the generated data not only has high accuracy and is valuable but can provide strong data support for the Internet of Vehicles and transportation research work. © 2021, Springer Nature Switzerland AG.
- Authors: Chen, Qiao , Ma, Kai , Hou, Mingliang , Kong, Xiangjie , Xia, Feng
- Date: 2021
- Type: Text , Conference paper
- Relation: 18th International Conference on Web Information Systems and Applications, WISA 2021 Vol. 12999 LNCS, p. 109-120
- Full Text:
- Reviewed:
- Description: In contrast with the condition that the trajectory dataset of floating cars (taxis) can be easily obtained from the Internet, it is hard to get the trajectory data of social vehicles (private vehicles) because of personal privacy and government policies. This paper absorbs the idea of game theory, considers the influence of individuals in the group, and proposes a decision behavior based dataset generation (DBDG) model of vehicles to predict future inter-regional traffic. In addition, we adopt simulation tools and generative adversarial networks to train the trajectory prediction model so that the private vehicle trajectory dataset conforming to social rules (e.g., collisionless) is generated. Finally, we construct from macroscopic and microscopic perspectives to verify dataset generation methods proposed in this paper. The results show that the generated data not only has high accuracy and is valuable but can provide strong data support for the Internet of Vehicles and transportation research work. © 2021, Springer Nature Switzerland AG.
Exploring human mobility for multi-pattern passenger prediction : a graph learning framework
- Kong, Xiangjiea, Wang, Kailai, Hou, Mingliang, Xia, Feng, Karmakar, Gour, Li, Jianxin
- Authors: Kong, Xiangjiea , Wang, Kailai , Hou, Mingliang , Xia, Feng , Karmakar, Gour , Li, Jianxin
- Date: 2022
- Type: Text , Journal article
- Relation: IEEE Transactions on Intelligent Transportation Systems Vol. 23, no. 9 (2022), p. 16148-16160
- Full Text:
- Reviewed:
- Description: Traffic flow prediction is an integral part of an intelligent transportation system and thus fundamental for various traffic-related applications. Buses are an indispensable way of moving for urban residents with fixed routes and schedules, which leads to latent travel regularity. However, human mobility patterns, specifically the complex relationships between bus passengers, are deeply hidden in this fixed mobility mode. Although many models exist to predict traffic flow, human mobility patterns have not been well explored in this regard. To address this research gap and learn human mobility knowledge from this fixed travel behaviors, we propose a multi-pattern passenger flow prediction framework, MPGCN, based on Graph Convolutional Network (GCN). Firstly, we construct a novel sharing-stop network to model relationships between passengers based on bus record data. Then, we employ GCN to extract features from the graph by learning useful topology information and introduce a deep clustering method to recognize mobility patterns hidden in bus passengers. Furthermore, to fully utilize spatio-temporal information, we propose GCN2Flow to predict passenger flow based on various mobility patterns. To the best of our knowledge, this paper is the first work to adopt a multi-pattern approach to predict the bus passenger flow by taking advantage of graph learning. We design a case study for optimizing routes. Extensive experiments upon a real-world bus dataset demonstrate that MPGCN has potential efficacy in passenger flow prediction and route optimization. © 2000-2011 IEEE.
- Authors: Kong, Xiangjiea , Wang, Kailai , Hou, Mingliang , Xia, Feng , Karmakar, Gour , Li, Jianxin
- Date: 2022
- Type: Text , Journal article
- Relation: IEEE Transactions on Intelligent Transportation Systems Vol. 23, no. 9 (2022), p. 16148-16160
- Full Text:
- Reviewed:
- Description: Traffic flow prediction is an integral part of an intelligent transportation system and thus fundamental for various traffic-related applications. Buses are an indispensable way of moving for urban residents with fixed routes and schedules, which leads to latent travel regularity. However, human mobility patterns, specifically the complex relationships between bus passengers, are deeply hidden in this fixed mobility mode. Although many models exist to predict traffic flow, human mobility patterns have not been well explored in this regard. To address this research gap and learn human mobility knowledge from this fixed travel behaviors, we propose a multi-pattern passenger flow prediction framework, MPGCN, based on Graph Convolutional Network (GCN). Firstly, we construct a novel sharing-stop network to model relationships between passengers based on bus record data. Then, we employ GCN to extract features from the graph by learning useful topology information and introduce a deep clustering method to recognize mobility patterns hidden in bus passengers. Furthermore, to fully utilize spatio-temporal information, we propose GCN2Flow to predict passenger flow based on various mobility patterns. To the best of our knowledge, this paper is the first work to adopt a multi-pattern approach to predict the bus passenger flow by taking advantage of graph learning. We design a case study for optimizing routes. Extensive experiments upon a real-world bus dataset demonstrate that MPGCN has potential efficacy in passenger flow prediction and route optimization. © 2000-2011 IEEE.
Network embedding : taxonomies, frameworks and applications
- Hou, Mingliang, Ren, Jing, Zhang, Da, Kong, Xiangjie, Zhang, Dongyu, Xia, Feng
- Authors: Hou, Mingliang , Ren, Jing , Zhang, Da , Kong, Xiangjie , Zhang, Dongyu , Xia, Feng
- Date: 2020
- Type: Text , Journal article , Review
- Relation: Computer Science Review Vol. 38, no. (2020), p.
- Full Text:
- Reviewed:
- Description: Networks are a general language for describing complex systems of interacting entities. In the real world, a network always contains massive nodes, edges and additional complex information which leads to high complexity in computing and analyzing tasks. Network embedding aims at transforming one network into a low dimensional vector space which benefits the downstream network analysis tasks. In this survey, we provide a systematic overview of network embedding techniques in addressing challenges appearing in networks. We first introduce concepts and challenges in network embedding. Afterwards, we categorize network embedding methods using three categories, including static homogeneous network embedding methods, static heterogeneous network embedding methods and dynamic network embedding methods. Next, we summarize the datasets and evaluation tasks commonly used in network embedding. Finally, we discuss several future directions in this field. © 2020 Elsevier Inc.
- Authors: Hou, Mingliang , Ren, Jing , Zhang, Da , Kong, Xiangjie , Zhang, Dongyu , Xia, Feng
- Date: 2020
- Type: Text , Journal article , Review
- Relation: Computer Science Review Vol. 38, no. (2020), p.
- Full Text:
- Reviewed:
- Description: Networks are a general language for describing complex systems of interacting entities. In the real world, a network always contains massive nodes, edges and additional complex information which leads to high complexity in computing and analyzing tasks. Network embedding aims at transforming one network into a low dimensional vector space which benefits the downstream network analysis tasks. In this survey, we provide a systematic overview of network embedding techniques in addressing challenges appearing in networks. We first introduce concepts and challenges in network embedding. Afterwards, we categorize network embedding methods using three categories, including static homogeneous network embedding methods, static heterogeneous network embedding methods and dynamic network embedding methods. Next, we summarize the datasets and evaluation tasks commonly used in network embedding. Finally, we discuss several future directions in this field. © 2020 Elsevier Inc.
RMGen : a tri-layer vehicular trajectory data generation model exploring urban region division and mobility pattern
- Kong, Xiangjie, Chen, Qiao, Hou, Mingliang, Rahim, Azizur, Ma, Kai, Xia, Feng
- Authors: Kong, Xiangjie , Chen, Qiao , Hou, Mingliang , Rahim, Azizur , Ma, Kai , Xia, Feng
- Date: 2022
- Type: Text , Journal article
- Relation: IEEE Transactions on Vehicular Technology Vol. 71, no. 9 (2022), p. 9225-9238
- Full Text:
- Reviewed:
- Description: As an important branch of the Internet of Things (IoT), the Internet of Vehicles (IoV) has attracted extensive attention in the research field. To deeply study the IoV and build a vehicle spatiotemporal interaction network, it is necessary to use the trajectory data of private cars. However, due to privacy and security protection policies and other reasons, the data set of private cars cannot be obtained, which hinders the research on the social attributes of vehicles in the IoV. Most of the previous work generated the same type of data, and how to generate private car data sets from various existing data sets is a huge challenge. In this paper, we propose a tri-layer framework to solve this problem. First, we propose a novel region division scheme that considers detailed inter-region relations connected by traffic flux. Second, a new spatial-temporal interaction model is developed to estimate the traffic flow between two regions. Third, we devise an evaluation pipeline to validate generation results from microscopic and macroscopic perspectives. Qualitative and quantitative results demonstrate that the data generated in heavy density scenarios can provide strong data support for downstream IoV and mobility research tasks. © 1967-2012 IEEE.
- Authors: Kong, Xiangjie , Chen, Qiao , Hou, Mingliang , Rahim, Azizur , Ma, Kai , Xia, Feng
- Date: 2022
- Type: Text , Journal article
- Relation: IEEE Transactions on Vehicular Technology Vol. 71, no. 9 (2022), p. 9225-9238
- Full Text:
- Reviewed:
- Description: As an important branch of the Internet of Things (IoT), the Internet of Vehicles (IoV) has attracted extensive attention in the research field. To deeply study the IoV and build a vehicle spatiotemporal interaction network, it is necessary to use the trajectory data of private cars. However, due to privacy and security protection policies and other reasons, the data set of private cars cannot be obtained, which hinders the research on the social attributes of vehicles in the IoV. Most of the previous work generated the same type of data, and how to generate private car data sets from various existing data sets is a huge challenge. In this paper, we propose a tri-layer framework to solve this problem. First, we propose a novel region division scheme that considers detailed inter-region relations connected by traffic flux. Second, a new spatial-temporal interaction model is developed to estimate the traffic flow between two regions. Third, we devise an evaluation pipeline to validate generation results from microscopic and macroscopic perspectives. Qualitative and quantitative results demonstrate that the data generated in heavy density scenarios can provide strong data support for downstream IoV and mobility research tasks. © 1967-2012 IEEE.
- «
- ‹
- 1
- ›
- »