Deep learning : survey of environmental and camera impacts on internet of things images
- Kaur, Roopdeep, Karmakar, Gour, Xia, Feng, Imran, Muhammad
- Authors: Kaur, Roopdeep , Karmakar, Gour , Xia, Feng , Imran, Muhammad
- Date: 2023
- Type: Text , Journal article
- Relation: Artificial Intelligence Review Vol. 56, no. 9 (2023), p. 9605-9638
- Full Text:
- Reviewed:
- Description: Internet of Things (IoT) images are captivating growing attention because of their wide range of applications which requires visual analysis to drive automation. However, IoT images are predominantly captured from outdoor environments and thus are inherently impacted by the camera and environmental parameters which can adversely affect corresponding applications. Deep Learning (DL) has been widely adopted in the field of image processing and computer vision and can reduce the impact of these parameters on IoT images. Albeit, there are many DL-based techniques available in the current literature for analyzing and reducing the environmental and camera impacts on IoT images. However, to the best of our knowledge, no survey paper presents state-of-the-art DL-based approaches for this purpose. Motivated by this, for the first time, we present a Systematic Literature Review (SLR) of existing DL techniques available for analyzing and reducing environmental and camera lens impacts on IoT images. As part of this SLR, firstly, we reiterate and highlight the significance of IoT images in their respective applications. Secondly, we describe the DL techniques employed for assessing the environmental and camera lens distortion impacts on IoT images. Thirdly, we illustrate how DL can be effective in reducing the impact of environmental and camera lens distortion in IoT images. Finally, along with the critical reflection on the advantages and limitations of the techniques, we also present ways to address the research challenges of existing techniques and identify some further researches to advance the relevant research areas. © 2023, The Author(s).
- Authors: Kaur, Roopdeep , Karmakar, Gour , Xia, Feng , Imran, Muhammad
- Date: 2023
- Type: Text , Journal article
- Relation: Artificial Intelligence Review Vol. 56, no. 9 (2023), p. 9605-9638
- Full Text:
- Reviewed:
- Description: Internet of Things (IoT) images are captivating growing attention because of their wide range of applications which requires visual analysis to drive automation. However, IoT images are predominantly captured from outdoor environments and thus are inherently impacted by the camera and environmental parameters which can adversely affect corresponding applications. Deep Learning (DL) has been widely adopted in the field of image processing and computer vision and can reduce the impact of these parameters on IoT images. Albeit, there are many DL-based techniques available in the current literature for analyzing and reducing the environmental and camera impacts on IoT images. However, to the best of our knowledge, no survey paper presents state-of-the-art DL-based approaches for this purpose. Motivated by this, for the first time, we present a Systematic Literature Review (SLR) of existing DL techniques available for analyzing and reducing environmental and camera lens impacts on IoT images. As part of this SLR, firstly, we reiterate and highlight the significance of IoT images in their respective applications. Secondly, we describe the DL techniques employed for assessing the environmental and camera lens distortion impacts on IoT images. Thirdly, we illustrate how DL can be effective in reducing the impact of environmental and camera lens distortion in IoT images. Finally, along with the critical reflection on the advantages and limitations of the techniques, we also present ways to address the research challenges of existing techniques and identify some further researches to advance the relevant research areas. © 2023, The Author(s).
Efficient anomaly recognition using surveillance videos
- Saleem, Gulshan, Bajwa, Usama, Raza, Rana, Alqahtani, Fayez, Tolba, Amr, Xia, Feng
- Authors: Saleem, Gulshan , Bajwa, Usama , Raza, Rana , Alqahtani, Fayez , Tolba, Amr , Xia, Feng
- Date: 2022
- Type: Text , Journal article
- Relation: PeerJ Computer Science Vol. 8, no. (2022), p.
- Full Text:
- Reviewed:
- Description: Smart surveillance is a difficult task that is gaining popularity due to its direct link to human safety. Today, many indoor and outdoor surveillance systems are in use at public places and smart cities. Because these systems are expensive to deploy, these are out of reach for the vast majority of the public and private sectors. Due to the lack of a precise definition of an anomaly, automated surveillance is a challenging task, especially when large amounts of data, such as 24/7 CCTV footage, must be processed. When implementing such systems in real-time environments, the high computational resource requirements for automated surveillance becomes a major bottleneck. Another challenge is to recognize anomalies accurately as achieving high accuracy while reducing computational cost is more challenging. To address these challenge, this research is based on the developing a system that is both efficient and cost effective. Although 3D convolutional neural networks have proven to be accurate, they are prohibitively expensive for practical use, particularly in real-time surveillance. In this article, we present two contributions: a resource-efficient framework for anomaly recognition problems and two-class and multi-class anomaly recognition on spatially augmented surveillance videos. This research aims to address the problem of computation overhead while maintaining recognition accuracy. The proposed Temporal based Anomaly Recognizer (TAR) framework combines a partial shift strategy with a 2D convolutional architecture-based model, namely MobileNetV2. Extensive experiments were carried out to evaluate the model's performance on the UCF Crime dataset, with MobileNetV2 as the baseline architecture; it achieved an accuracy of 88% which is 2.47% increased performance than available state-of-the-art. The proposed framework achieves 52.7% accuracy for multiclass anomaly recognition on the UCF Crime2Local dataset. The proposed model has been tested in real-time camera stream settings and can handle six streams simultaneously without the need for additional resources. © Copyright 2022 Saleem et al.
- Authors: Saleem, Gulshan , Bajwa, Usama , Raza, Rana , Alqahtani, Fayez , Tolba, Amr , Xia, Feng
- Date: 2022
- Type: Text , Journal article
- Relation: PeerJ Computer Science Vol. 8, no. (2022), p.
- Full Text:
- Reviewed:
- Description: Smart surveillance is a difficult task that is gaining popularity due to its direct link to human safety. Today, many indoor and outdoor surveillance systems are in use at public places and smart cities. Because these systems are expensive to deploy, these are out of reach for the vast majority of the public and private sectors. Due to the lack of a precise definition of an anomaly, automated surveillance is a challenging task, especially when large amounts of data, such as 24/7 CCTV footage, must be processed. When implementing such systems in real-time environments, the high computational resource requirements for automated surveillance becomes a major bottleneck. Another challenge is to recognize anomalies accurately as achieving high accuracy while reducing computational cost is more challenging. To address these challenge, this research is based on the developing a system that is both efficient and cost effective. Although 3D convolutional neural networks have proven to be accurate, they are prohibitively expensive for practical use, particularly in real-time surveillance. In this article, we present two contributions: a resource-efficient framework for anomaly recognition problems and two-class and multi-class anomaly recognition on spatially augmented surveillance videos. This research aims to address the problem of computation overhead while maintaining recognition accuracy. The proposed Temporal based Anomaly Recognizer (TAR) framework combines a partial shift strategy with a 2D convolutional architecture-based model, namely MobileNetV2. Extensive experiments were carried out to evaluate the model's performance on the UCF Crime dataset, with MobileNetV2 as the baseline architecture; it achieved an accuracy of 88% which is 2.47% increased performance than available state-of-the-art. The proposed framework achieves 52.7% accuracy for multiclass anomaly recognition on the UCF Crime2Local dataset. The proposed model has been tested in real-time camera stream settings and can handle six streams simultaneously without the need for additional resources. © Copyright 2022 Saleem et al.
Graph self-supervised learning : a survey
- Liu, Yixin, Jin, Ming, Pan, Shirui, Zhou, Chuan, Zheng, Yu, Xia, Feng, Yu, Philip
- Authors: Liu, Yixin , Jin, Ming , Pan, Shirui , Zhou, Chuan , Zheng, Yu , Xia, Feng , Yu, Philip
- Date: 2022
- Type: Text , Journal article
- Relation: IEEE Transactions on Knowledge and Data Engineering Vol. 35, no. 6 (2022), p. 5879-5900
- Full Text:
- Reviewed:
- Description: Deep learning on graphs has attracted significant interests recently. However, most of the works have focused on (semi-) supervised learning, resulting in shortcomings including heavy label reliance, poor generalization, and weak robustness. To address these issues, self-supervised learning (SSL), which extracts informative knowledge through well-designed pretext tasks without relying on manual labels, has become a promising and trending learning paradigm for graph data. Different from SSL on other domains like computer vision and natural language processing, SSL on graphs has an exclusive background, design ideas, and taxonomies. Under the umbrella of graph self-supervised learning, we present a timely and comprehensive review of the existing approaches which employ SSL techniques for graph data. We construct a unified framework that mathematically formalizes the paradigm of graph SSL. According to the objectives of pretext tasks, we divide these approaches into four categories: generation-based, auxiliary property-based, contrast-based, and hybrid approaches. We further describe the applications of graph SSL across various research fields and summarize the commonly used datasets, evaluation benchmark, performance comparison and open-source codes of graph SSL. Finally, we discuss the remaining challenges and potential future directions in this research field. IEEE
- Authors: Liu, Yixin , Jin, Ming , Pan, Shirui , Zhou, Chuan , Zheng, Yu , Xia, Feng , Yu, Philip
- Date: 2022
- Type: Text , Journal article
- Relation: IEEE Transactions on Knowledge and Data Engineering Vol. 35, no. 6 (2022), p. 5879-5900
- Full Text:
- Reviewed:
- Description: Deep learning on graphs has attracted significant interests recently. However, most of the works have focused on (semi-) supervised learning, resulting in shortcomings including heavy label reliance, poor generalization, and weak robustness. To address these issues, self-supervised learning (SSL), which extracts informative knowledge through well-designed pretext tasks without relying on manual labels, has become a promising and trending learning paradigm for graph data. Different from SSL on other domains like computer vision and natural language processing, SSL on graphs has an exclusive background, design ideas, and taxonomies. Under the umbrella of graph self-supervised learning, we present a timely and comprehensive review of the existing approaches which employ SSL techniques for graph data. We construct a unified framework that mathematically formalizes the paradigm of graph SSL. According to the objectives of pretext tasks, we divide these approaches into four categories: generation-based, auxiliary property-based, contrast-based, and hybrid approaches. We further describe the applications of graph SSL across various research fields and summarize the commonly used datasets, evaluation benchmark, performance comparison and open-source codes of graph SSL. Finally, we discuss the remaining challenges and potential future directions in this research field. IEEE
Subgraph adaptive structure-aware graph contrastive learning
- Chen, Zhikui, Peng, Yin, Yu, Shuo, Cao, Chen, Xia, Feng
- Authors: Chen, Zhikui , Peng, Yin , Yu, Shuo , Cao, Chen , Xia, Feng
- Date: 2022
- Type: Text , Journal article
- Relation: Mathematics (Basel) Vol. 10, no. 17 (2022), p. 3047
- Full Text:
- Reviewed:
- Description: Graph contrastive learning (GCL) has been subject to more attention and been widely applied to numerous graph learning tasks such as node classification and link prediction. Although it has achieved great success and even performed better than supervised methods in some tasks, most of them depend on node-level comparison, while ignoring the rich semantic information contained in graph topology, especially for social networks. However, a higher-level comparison requires subgraph construction and encoding, which remain unsolved. To address this problem, we propose a subgraph adaptive structure-aware graph contrastive learning method (PASCAL) in this work, which is a subgraph-level GCL method. In PASCAL, we construct subgraphs by merging all motifs that contain the target node. Then we encode them on the basis of motif number distribution to capture the rich information hidden in subgraphs. By incorporating motif information, PASCAL can capture richer semantic information hidden in local structures compared with other GCL methods. Extensive experiments on six benchmark datasets show that PASCAL outperforms state-of-art graph contrastive learning and supervised methods in most cases.
- Authors: Chen, Zhikui , Peng, Yin , Yu, Shuo , Cao, Chen , Xia, Feng
- Date: 2022
- Type: Text , Journal article
- Relation: Mathematics (Basel) Vol. 10, no. 17 (2022), p. 3047
- Full Text:
- Reviewed:
- Description: Graph contrastive learning (GCL) has been subject to more attention and been widely applied to numerous graph learning tasks such as node classification and link prediction. Although it has achieved great success and even performed better than supervised methods in some tasks, most of them depend on node-level comparison, while ignoring the rich semantic information contained in graph topology, especially for social networks. However, a higher-level comparison requires subgraph construction and encoding, which remain unsolved. To address this problem, we propose a subgraph adaptive structure-aware graph contrastive learning method (PASCAL) in this work, which is a subgraph-level GCL method. In PASCAL, we construct subgraphs by merging all motifs that contain the target node. Then we encode them on the basis of motif number distribution to capture the rich information hidden in subgraphs. By incorporating motif information, PASCAL can capture richer semantic information hidden in local structures compared with other GCL methods. Extensive experiments on six benchmark datasets show that PASCAL outperforms state-of-art graph contrastive learning and supervised methods in most cases.
Deep matrix factorization for trust-aware recommendation in social networks
- Wan, Liangtian, Xia, Feng, Kong, Xiangjie, Hsu, Ching-Hsien, Huang, Runhe, Ma, Jianhua
- Authors: Wan, Liangtian , Xia, Feng , Kong, Xiangjie , Hsu, Ching-Hsien , Huang, Runhe , Ma, Jianhua
- Date: 2021
- Type: Text , Journal article
- Relation: IEEE Transactions on Network Science and Engineering Vol. 8, no. 1 (2021), p. 511-528
- Full Text:
- Reviewed:
- Description: Recent years have witnessed remarkable information overload in online social networks, and social network based approaches for recommender systems have been widely studied. The trust information in social networks among users is an important factor for improving recommendation performance. Many successful recommendation tasks are treated as the matrix factorization problems. However, the prediction performance of matrix factorization based methods largely depends on the matrixes initialization of users and items. To address this challenge, we develop a novel trust-aware approach based on deep learning to alleviate the initialization dependence. First, we propose two deep matrix factorization (DMF) techniques, i.e., linear DMF and non-linear DMF to extract features from the user-item rating matrix for improving the initialization accuracy. The trust relationship is integrated into the DMF model according to the preference similarity and the derivations of users on items. Second, we exploit deep marginalized Denoising Autoencoder (Deep-MDAE) to extract the latent representation in the hidden layer from the trust relationship matrix to approximate the user factor matrix factorized from the user-item rating matrix. The community regularization is integrated in the joint optimization function to take neighbours' effects into consideration. The results of DMF are applied to initialize the updating variables of Deep-MDAE in order to further improve the recommendation performance. Finally, we validate that the proposed approach outperforms state-of-the-art baselines for recommendation, especially for the cold-start users. © 2013 IEEE.
- Authors: Wan, Liangtian , Xia, Feng , Kong, Xiangjie , Hsu, Ching-Hsien , Huang, Runhe , Ma, Jianhua
- Date: 2021
- Type: Text , Journal article
- Relation: IEEE Transactions on Network Science and Engineering Vol. 8, no. 1 (2021), p. 511-528
- Full Text:
- Reviewed:
- Description: Recent years have witnessed remarkable information overload in online social networks, and social network based approaches for recommender systems have been widely studied. The trust information in social networks among users is an important factor for improving recommendation performance. Many successful recommendation tasks are treated as the matrix factorization problems. However, the prediction performance of matrix factorization based methods largely depends on the matrixes initialization of users and items. To address this challenge, we develop a novel trust-aware approach based on deep learning to alleviate the initialization dependence. First, we propose two deep matrix factorization (DMF) techniques, i.e., linear DMF and non-linear DMF to extract features from the user-item rating matrix for improving the initialization accuracy. The trust relationship is integrated into the DMF model according to the preference similarity and the derivations of users on items. Second, we exploit deep marginalized Denoising Autoencoder (Deep-MDAE) to extract the latent representation in the hidden layer from the trust relationship matrix to approximate the user factor matrix factorized from the user-item rating matrix. The community regularization is integrated in the joint optimization function to take neighbours' effects into consideration. The results of DMF are applied to initialize the updating variables of Deep-MDAE in order to further improve the recommendation performance. Finally, we validate that the proposed approach outperforms state-of-the-art baselines for recommendation, especially for the cold-start users. © 2013 IEEE.
Deep video anomaly detection : opportunities and challenges
- Ren, Jing, Xia, Feng, Liu, Yemeng, Lee, Ivan
- Authors: Ren, Jing , Xia, Feng , Liu, Yemeng , Lee, Ivan
- 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. 959-966
- Full Text:
- Reviewed:
- Description: Anomaly detection is a popular and vital task in various research contexts, which has been studied for several decades. To ensure the safety of people's lives and assets, video surveillance has been widely deployed in various public spaces, such as crossroads, elevators, hospitals, banks, and even in private homes. Deep learning has shown its capacity in a number of domains, ranging from acoustics, images, to natural language processing. However, it is non-trivial to devise intelligent video anomaly detection systems cause anomalies significantly differ from each other in different application scenarios. There are numerous advantages if such intelligent systems could be realised in our daily lives, such as saving human resources in a large degree, reducing financial burden on the government, and identifying the anomalous behaviours timely and accurately. Recently, many studies on extending deep learning models for solving anomaly detection problems have emerged, resulting in beneficial advances in deep video anomaly detection techniques. In this paper, we present a comprehensive review of deep learning-based methods to detect the video anomalies from a new perspective. Specifically, we summarise the opportunities and challenges of deep learning models on video anomaly detection tasks, respectively. We put forth several potential future research directions of intelligent video anomaly detection system in various application domains. Moreover, we summarise the characteristics and technical problems in current deep learning methods for video anomaly detection. © 2021 IEEE.
- Authors: Ren, Jing , Xia, Feng , Liu, Yemeng , Lee, Ivan
- 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. 959-966
- Full Text:
- Reviewed:
- Description: Anomaly detection is a popular and vital task in various research contexts, which has been studied for several decades. To ensure the safety of people's lives and assets, video surveillance has been widely deployed in various public spaces, such as crossroads, elevators, hospitals, banks, and even in private homes. Deep learning has shown its capacity in a number of domains, ranging from acoustics, images, to natural language processing. However, it is non-trivial to devise intelligent video anomaly detection systems cause anomalies significantly differ from each other in different application scenarios. There are numerous advantages if such intelligent systems could be realised in our daily lives, such as saving human resources in a large degree, reducing financial burden on the government, and identifying the anomalous behaviours timely and accurately. Recently, many studies on extending deep learning models for solving anomaly detection problems have emerged, resulting in beneficial advances in deep video anomaly detection techniques. In this paper, we present a comprehensive review of deep learning-based methods to detect the video anomalies from a new perspective. Specifically, we summarise the opportunities and challenges of deep learning models on video anomaly detection tasks, respectively. We put forth several potential future research directions of intelligent video anomaly detection system in various application domains. Moreover, we summarise the characteristics and technical problems in current deep learning methods for video anomaly detection. © 2021 IEEE.
Graph learning : a survey
- Xia, Feng, Sun, Ke, Yu, Shuo, Aziz, Abdul, Wan, Liangtian, Pan, Shirui, Liu, Huan
- Authors: Xia, Feng , Sun, Ke , Yu, Shuo , Aziz, Abdul , Wan, Liangtian , Pan, Shirui , Liu, Huan
- Date: 2021
- Type: Text , Journal article , Review
- Relation: IEEE Transactions on Artificial Intelligence Vol. 2, no. 2 (2021), p. 109-127
- Full Text:
- Reviewed:
- Description: Graphs are widely used as a popular representation of the network structure of connected data. Graph data can be found in a broad spectrum of application domains such as social systems, ecosystems, biological networks, knowledge graphs, and information systems. With the continuous penetration of artificial intelligence technologies, graph learning (i.e., machine learning on graphs) is gaining attention from both researchers and practitioners. Graph learning proves effective for many tasks, such as classification, link prediction, and matching. Generally, graph learning methods extract relevant features of graphs by taking advantage of machine learning algorithms. In this survey, we present a comprehensive overview on the state-of-the-art of graph learning. Special attention is paid to four categories of existing graph learning methods, including graph signal processing, matrix factorization, random walk, and deep learning. Major models and algorithms under these categories are reviewed, respectively. We examine graph learning applications in areas such as text, images, science, knowledge graphs, and combinatorial optimization. In addition, we discuss several promising research directions in this field. Impact Statement—Real-world intelligent systems generally rely on machine learning algorithms handling data of various types. Despite their ubiquity, graph data have imposed unprecedented challenges to machine learning due to their inherent complexity. Unlike text, audio and images, graph data are embedded in an irregular domain, making some essential operations of existing machine learning algorithms inapplicable. Many graph learning models and algorithms have been developed to tackle these challenges. This article presents a systematic review of the state-of-the-art graph learning approaches as well as their potential applications. The article serves multiple purposes. First, it acts as a quick reference to graph learning for researchers and practitioners in different areas such as social computing, information retrieval, computer vision, bioinformatics, economics, and e-commence. Second, it presents insights into open areas of research in the field. Third, it aims to stimulate new research ideas and more interests in graph learning. © IEEE Transactions on Artificial Intelligence 2020.
- Authors: Xia, Feng , Sun, Ke , Yu, Shuo , Aziz, Abdul , Wan, Liangtian , Pan, Shirui , Liu, Huan
- Date: 2021
- Type: Text , Journal article , Review
- Relation: IEEE Transactions on Artificial Intelligence Vol. 2, no. 2 (2021), p. 109-127
- Full Text:
- Reviewed:
- Description: Graphs are widely used as a popular representation of the network structure of connected data. Graph data can be found in a broad spectrum of application domains such as social systems, ecosystems, biological networks, knowledge graphs, and information systems. With the continuous penetration of artificial intelligence technologies, graph learning (i.e., machine learning on graphs) is gaining attention from both researchers and practitioners. Graph learning proves effective for many tasks, such as classification, link prediction, and matching. Generally, graph learning methods extract relevant features of graphs by taking advantage of machine learning algorithms. In this survey, we present a comprehensive overview on the state-of-the-art of graph learning. Special attention is paid to four categories of existing graph learning methods, including graph signal processing, matrix factorization, random walk, and deep learning. Major models and algorithms under these categories are reviewed, respectively. We examine graph learning applications in areas such as text, images, science, knowledge graphs, and combinatorial optimization. In addition, we discuss several promising research directions in this field. Impact Statement—Real-world intelligent systems generally rely on machine learning algorithms handling data of various types. Despite their ubiquity, graph data have imposed unprecedented challenges to machine learning due to their inherent complexity. Unlike text, audio and images, graph data are embedded in an irregular domain, making some essential operations of existing machine learning algorithms inapplicable. Many graph learning models and algorithms have been developed to tackle these challenges. This article presents a systematic review of the state-of-the-art graph learning approaches as well as their potential applications. The article serves multiple purposes. First, it acts as a quick reference to graph learning for researchers and practitioners in different areas such as social computing, information retrieval, computer vision, bioinformatics, economics, and e-commence. Second, it presents insights into open areas of research in the field. Third, it aims to stimulate new research ideas and more interests in graph learning. © IEEE Transactions on Artificial Intelligence 2020.
Tracing the Pace of COVID-19 research : topic modeling and evolution
- Liu, Jiaying, Nie, Hansong, Li, Shihao, Ren, Jing, Xia, Feng
- Authors: Liu, Jiaying , Nie, Hansong , Li, Shihao , Ren, Jing , Xia, Feng
- Date: 2021
- Type: Text , Journal article
- Relation: Big Data Research Vol. 25, no. (2021), p.
- Full Text:
- Reviewed:
- Description: COVID-19 has been spreading rapidly around the world. With the growing attention on the deadly pandemic, discussions and research on COVID-19 are rapidly increasing to exchange latest findings with the hope to accelerate the pace of finding a cure. As a branch of information technology, artificial intelligence (AI) has greatly expedited the development of human society. In this paper, we investigate and visualize the on-going advancements of early scientific research on COVID-19 from the perspective of AI. By adopting the Latent Dirichlet Allocation (LDA) model, this paper allocates the research articles into 50 key research topics pertinent to COVID-19 according to their abstracts. We present an overview of early studies of the COVID-19 crisis at different scales including referencing/citation behavior, topic variation and their inner interactions. We also identify innovative papers that are regarded as the cornerstones in the development of COVID-19 research. The results unveil the focus of scientific research, thereby giving deep insights into how the academic society contributes to combating the COVID-19 pandemic. © 2021 Elsevier Inc. **Please note that there are multiple authors for this article therefore only the name of the first 5 including Federation University Australia affiliate “Jing Ren and Feng Xia" is provided in this record**
- Description: COVID-19 has been spreading rapidly around the world. With the growing attention on the deadly pandemic, discussions and research on COVID-19 are rapidly increasing to exchange latest findings with the hope to accelerate the pace of finding a cure. As a branch of information technology, artificial intelligence (AI) has greatly expedited the development of human society. In this paper, we investigate and visualize the on-going advancements of early scientific research on COVID-19 from the perspective of AI. By adopting the Latent Dirichlet Allocation (LDA) model, this paper allocates the research articles into 50 key research topics pertinent to COVID-19 according to their abstracts. We present an overview of early studies of the COVID-19 crisis at different scales including referencing/citation behavior, topic variation and their inner interactions. We also identify innovative papers that are regarded as the cornerstones in the development of COVID-19 research. The results unveil the focus of scientific research, thereby giving deep insights into how the academic society contributes to combating the COVID-19 pandemic. © 2021 Elsevier Inc.
- Authors: Liu, Jiaying , Nie, Hansong , Li, Shihao , Ren, Jing , Xia, Feng
- Date: 2021
- Type: Text , Journal article
- Relation: Big Data Research Vol. 25, no. (2021), p.
- Full Text:
- Reviewed:
- Description: COVID-19 has been spreading rapidly around the world. With the growing attention on the deadly pandemic, discussions and research on COVID-19 are rapidly increasing to exchange latest findings with the hope to accelerate the pace of finding a cure. As a branch of information technology, artificial intelligence (AI) has greatly expedited the development of human society. In this paper, we investigate and visualize the on-going advancements of early scientific research on COVID-19 from the perspective of AI. By adopting the Latent Dirichlet Allocation (LDA) model, this paper allocates the research articles into 50 key research topics pertinent to COVID-19 according to their abstracts. We present an overview of early studies of the COVID-19 crisis at different scales including referencing/citation behavior, topic variation and their inner interactions. We also identify innovative papers that are regarded as the cornerstones in the development of COVID-19 research. The results unveil the focus of scientific research, thereby giving deep insights into how the academic society contributes to combating the COVID-19 pandemic. © 2021 Elsevier Inc. **Please note that there are multiple authors for this article therefore only the name of the first 5 including Federation University Australia affiliate “Jing Ren and Feng Xia" is provided in this record**
- Description: COVID-19 has been spreading rapidly around the world. With the growing attention on the deadly pandemic, discussions and research on COVID-19 are rapidly increasing to exchange latest findings with the hope to accelerate the pace of finding a cure. As a branch of information technology, artificial intelligence (AI) has greatly expedited the development of human society. In this paper, we investigate and visualize the on-going advancements of early scientific research on COVID-19 from the perspective of AI. By adopting the Latent Dirichlet Allocation (LDA) model, this paper allocates the research articles into 50 key research topics pertinent to COVID-19 according to their abstracts. We present an overview of early studies of the COVID-19 crisis at different scales including referencing/citation behavior, topic variation and their inner interactions. We also identify innovative papers that are regarded as the cornerstones in the development of COVID-19 research. The results unveil the focus of scientific research, thereby giving deep insights into how the academic society contributes to combating the COVID-19 pandemic. © 2021 Elsevier Inc.
MODEL : motif-based deep feature learning for link prediction
- Wang, Lei, Ren, Jing, Xu, Bo, Li, Jianxin, Luo, Wei, Xia, Feng
- Authors: Wang, Lei , Ren, Jing , Xu, Bo , Li, Jianxin , Luo, Wei , Xia, Feng
- Date: 2020
- Type: Text , Journal article
- Relation: IEEE Transactions on Computational Social Systems Vol. 7, no. 2 (2020), p. 503-516
- Full Text:
- Reviewed:
- Description: Link prediction plays an important role in network analysis and applications. Recently, approaches for link prediction have evolved from traditional similarity-based algorithms into embedding-based algorithms. However, most existing approaches fail to exploit the fact that real-world networks are different from random networks. In particular, real-world networks are known to contain motifs, natural network building blocks reflecting the underlying network-generating processes. In this article, we propose a novel embedding algorithm that incorporates network motifs to capture higher order structures in the network. To evaluate its effectiveness for link prediction, experiments were conducted on three types of networks: social networks, biological networks, and academic networks. The results demonstrate that our algorithm outperforms both the traditional similarity-based algorithms (by 20%) and the state-of-the-art embedding-based algorithms (by 19%). © 2014 IEEE.
- Authors: Wang, Lei , Ren, Jing , Xu, Bo , Li, Jianxin , Luo, Wei , Xia, Feng
- Date: 2020
- Type: Text , Journal article
- Relation: IEEE Transactions on Computational Social Systems Vol. 7, no. 2 (2020), p. 503-516
- Full Text:
- Reviewed:
- Description: Link prediction plays an important role in network analysis and applications. Recently, approaches for link prediction have evolved from traditional similarity-based algorithms into embedding-based algorithms. However, most existing approaches fail to exploit the fact that real-world networks are different from random networks. In particular, real-world networks are known to contain motifs, natural network building blocks reflecting the underlying network-generating processes. In this article, we propose a novel embedding algorithm that incorporates network motifs to capture higher order structures in the network. To evaluate its effectiveness for link prediction, experiments were conducted on three types of networks: social networks, biological networks, and academic networks. The results demonstrate that our algorithm outperforms both the traditional similarity-based algorithms (by 20%) and the state-of-the-art embedding-based algorithms (by 19%). © 2014 IEEE.
Network representation learning: From traditional feature learning to deep learning
- Sun, Ke, Wang, Lei, Xu, Bo, Zhao, Wenhong, Teng, Shyh, Xia, Feng
- Authors: Sun, Ke , Wang, Lei , Xu, Bo , Zhao, Wenhong , Teng, Shyh , Xia, Feng
- Date: 2020
- Type: Text , Journal article
- Relation: IEEE Access Vol. 8, no. (2020), p. 205600-205617
- Full Text:
- Reviewed:
- Description: Network representation learning (NRL) is an effective graph analytics technique and promotes users to deeply understand the hidden characteristics of graph data. It has been successfully applied in many real-world tasks related to network science, such as social network data processing, biological information processing, and recommender systems. Deep Learning is a powerful tool to learn data features. However, it is non-trivial to generalize deep learning to graph-structured data since it is different from the regular data such as pictures having spatial information and sounds having temporal information. Recently, researchers proposed many deep learning-based methods in the area of NRL. In this survey, we investigate classical NRL from traditional feature learning method to the deep learning-based model, analyze relationships between them, and summarize the latest progress. Finally, we discuss open issues considering NRL and point out the future directions in this field. © 2020 Institute of Electrical and Electronics Engineers Inc.. All rights reserved.
- Authors: Sun, Ke , Wang, Lei , Xu, Bo , Zhao, Wenhong , Teng, Shyh , Xia, Feng
- Date: 2020
- Type: Text , Journal article
- Relation: IEEE Access Vol. 8, no. (2020), p. 205600-205617
- Full Text:
- Reviewed:
- Description: Network representation learning (NRL) is an effective graph analytics technique and promotes users to deeply understand the hidden characteristics of graph data. It has been successfully applied in many real-world tasks related to network science, such as social network data processing, biological information processing, and recommender systems. Deep Learning is a powerful tool to learn data features. However, it is non-trivial to generalize deep learning to graph-structured data since it is different from the regular data such as pictures having spatial information and sounds having temporal information. Recently, researchers proposed many deep learning-based methods in the area of NRL. In this survey, we investigate classical NRL from traditional feature learning method to the deep learning-based model, analyze relationships between them, and summarize the latest progress. Finally, we discuss open issues considering NRL and point out the future directions in this field. © 2020 Institute of Electrical and Electronics Engineers Inc.. All rights reserved.
DINE : a framework for deep incomplete network embedding
- Hou, Ke, Liu, Jiaying, Peng, Yin, Xu, Bo, Lee, Ivan, Xia, Feng
- Authors: Hou, Ke , Liu, Jiaying , Peng, Yin , Xu, Bo , Lee, Ivan , Xia, Feng
- Date: 2019
- Type: Text , Conference paper
- Relation: 32nd Australasian Joint Conference on Artificial Intelligence, AI 2019 Vol. 11919 LNAI, p. 165-176
- Full Text:
- Reviewed:
- Description: Network representation learning (NRL) plays a vital role in a variety of tasks such as node classification and link prediction. It aims to learn low-dimensional vector representations for nodes based on network structures or node attributes. While embedding techniques on complete networks have been intensively studied, in real-world applications, it is still a challenging task to collect complete networks. To bridge the gap, in this paper, we propose a Deep Incomplete Network Embedding method, namely DINE. Specifically, we first complete the missing part including both nodes and edges in a partially observable network by using the expectation-maximization framework. To improve the embedding performance, we consider both network structures and node attributes to learn node representations. Empirically, we evaluate DINE over three networks on multi-label classification and link prediction tasks. The results demonstrate the superiority of our proposed approach compared against state-of-the-art baselines. © 2019, Springer Nature Switzerland AG.
- Description: E1
- Authors: Hou, Ke , Liu, Jiaying , Peng, Yin , Xu, Bo , Lee, Ivan , Xia, Feng
- Date: 2019
- Type: Text , Conference paper
- Relation: 32nd Australasian Joint Conference on Artificial Intelligence, AI 2019 Vol. 11919 LNAI, p. 165-176
- Full Text:
- Reviewed:
- Description: Network representation learning (NRL) plays a vital role in a variety of tasks such as node classification and link prediction. It aims to learn low-dimensional vector representations for nodes based on network structures or node attributes. While embedding techniques on complete networks have been intensively studied, in real-world applications, it is still a challenging task to collect complete networks. To bridge the gap, in this paper, we propose a Deep Incomplete Network Embedding method, namely DINE. Specifically, we first complete the missing part including both nodes and edges in a partially observable network by using the expectation-maximization framework. To improve the embedding performance, we consider both network structures and node attributes to learn node representations. Empirically, we evaluate DINE over three networks on multi-label classification and link prediction tasks. The results demonstrate the superiority of our proposed approach compared against state-of-the-art baselines. © 2019, Springer Nature Switzerland AG.
- Description: E1
- «
- ‹
- 1
- ›
- »