Zhuoqing Chang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Zhuoqing Chang has a total of 10 co-authors. Here are the top co-authors by number of shared publications:
- Shubo Liu
Wuhan University
5 shared publications - Zhaohui Cai
School of Computer Science, Wuhan University, Wuhan, China
3 shared publications Guoqing Tu
Wuhan University
2 shared publications- Guoqing Tu
School of Cyber Science and Engineering, Wuhan University, Wuhan, China
2 shared publications - Guoqing Tu
School of Cyber Science and Engineering, Wuhan University, Wuhan, China
1 shared publication - Run Qiu
School of Computer Science, Wuhan University, Wuhan, China
1 shared publication
Latest Publications
- 18 November 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 12 (7) , 8552-8569
Continuous Latent Adversarial Autoencoder: A Time-Sensitive Method for Incomplete Time-Series Modeling
Incomplete time-series modeling is an unavoidable topic in real-world time-series analysis because of the frequent occurrence of missing values in practical data. However, integrating data preprocessing and subsequent analysis within a model can amplify the errors from processed values. Moreover, most existing methods that directly model incomplete time series often fail to infer values at any desired time or support multistep prediction. To address these issues, this article introduces a novel generative model called the continuous latent adversarial autoencoder (CLAAE) for directly modeling incomplete time series. CLAAE can effectively impute missing data of any time point and support multistep prediction. Specifically, CLAAE devises a time-aware long short-term memory (LSTM) encoder to extract temporal and sequential characteristics. The decoder is built upon the augmented neural ordinary differential equation (ANODE), allowing it to infer the probability of missing data across an arbitrary continuous-time horizon. To guarantee the meaningfulness of samples generated from any region within the prior space, a fully connected neural network is utilized as a discriminator, encouraging the aggregated posterior learned by the encoder to be indistinguishable from a selected prior distribution. Extensive experimental results across simulations and real-world datasets demonstrate that CLAAE outperforms baseline methods, especially when the amount of missing data is overwhelming. By combining the autoencoder and adversarial training, CLAAE can significantly enhance the quality of the synthetic samples, respecting the original feature distributions and the temporal dynamics.
- 18 November 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 12 (7) , 8552-8569
Continuous Latent Adversarial Autoencoder: A Time-Sensitive Method for Incomplete Time-Series Modeling
Incomplete time-series modeling is an unavoidable topic in real-world time-series analysis because of the frequent occurrence of missing values in practical data. However, integrating data preprocessing and subsequent analysis within a model can amplify the errors from processed values. Moreover, most existing methods that directly model incomplete time series often fail to infer values at any desired time or support multistep prediction. To address these issues, this article introduces a novel generative model called the continuous latent adversarial autoencoder (CLAAE) for directly modeling incomplete time series. CLAAE can effectively impute missing data of any time point and support multistep prediction. Specifically, CLAAE devises a time-aware long short-term memory (LSTM) encoder to extract temporal and sequential characteristics. The decoder is built upon the augmented neural ordinary differential equation (ANODE), allowing it to infer the probability of missing data across an arbitrary continuous-time horizon. To guarantee the meaningfulness of samples generated from any region within the prior space, a fully connected neural network is utilized as a discriminator, encouraging the aggregated posterior learned by the encoder to be indistinguishable from a selected prior distribution. Extensive experimental results across simulations and real-world datasets demonstrate that CLAAE outperforms baseline methods, especially when the amount of missing data is overwhelming. By combining the autoencoder and adversarial training, CLAAE can significantly enhance the quality of the synthetic samples, respecting the original feature distributions and the temporal dynamics.
- 17 September 2024
- Published by Springer Nature
- p. 175-189
Missing Data Imputation via Neighbor Data Feature-Enriched Neural Ordinary Differential Equations
- 17 September 2024
- Published by Springer Nature
- p. 175-189
Missing Data Imputation via Neighbor Data Feature-Enriched Neural Ordinary Differential Equations
- 22 September 2023
- Published by Springer Nature
- p. 16-27
ANODE-GAN: Incomplete Time Series Imputation by Augmented Neural ODE-Based Generative Adversarial Networks
- 22 September 2023
- Published by Springer Nature
- p. 16-27
ANODE-GAN: Incomplete Time Series Imputation by Augmented Neural ODE-Based Generative Adversarial Networks
- 18 May 2023
- Published by Springer Nature in The Journal of Supercomputing
- Vol. 79 (16) , 18699-18727
Time-aware neural ordinary differential equations for incomplete time series modeling
Internet of Things realizes the ubiquitous connection of all things, generating countless time-tagged data called time series. However, real-world time series are often plagued with missing values on account of noise or malfunctioning sensors. Existing methods for modeling such incomplete time series typically involve preprocessing steps, such as deletion or missing data imputation using statistical learning or machine learning methods. Unfortunately, these methods unavoidable destroy time information and bring error accumulation to the subsequent model. To this end, this paper introduces a novel continuous neural network architecture, named Time-aware Neural-Ordinary Differential Equations (TN-ODE), for incomplete time data modeling. The proposed method not only supports imputation missing values at arbitrary time points, but also enables multi-step prediction at desired time points. Specifically, TN-ODE employs a time-aware Long Short-Term Memory as an encoder, which effectively learns the posterior distribution from partial observed data. Additionally, the derivative of latent states is parameterized with a fully connected network, thereby enabling continuous-time latent dynamics generation. The proposed TN-ODE model is evaluated on both real-world and synthetic incomplete time-series datasets by conducting data interpolation and extrapolation tasks as well as classification task. Extensive experiments show the TN-ODE model outperforms baseline methods in terms of Mean Square Error for imputation and prediction tasks, as well as accuracy in downstream classification task.
- 18 May 2023
- Published by Springer Nature in The Journal of Supercomputing
- Vol. 79 (16) , 18699-18727
Time-aware neural ordinary differential equations for incomplete time series modeling
Internet of Things realizes the ubiquitous connection of all things, generating countless time-tagged data called time series. However, real-world time series are often plagued with missing values on account of noise or malfunctioning sensors. Existing methods for modeling such incomplete time series typically involve preprocessing steps, such as deletion or missing data imputation using statistical learning or machine learning methods. Unfortunately, these methods unavoidable destroy time information and bring error accumulation to the subsequent model. To this end, this paper introduces a novel continuous neural network architecture, named Time-aware Neural-Ordinary Differential Equations (TN-ODE), for incomplete time data modeling. The proposed method not only supports imputation missing values at arbitrary time points, but also enables multi-step prediction at desired time points. Specifically, TN-ODE employs a time-aware Long Short-Term Memory as an encoder, which effectively learns the posterior distribution from partial observed data. Additionally, the derivative of latent states is parameterized with a fully connected network, thereby enabling continuous-time latent dynamics generation. The proposed TN-ODE model is evaluated on both real-world and synthetic incomplete time-series datasets by conducting data interpolation and extrapolation tasks as well as classification task. Extensive experiments show the TN-ODE model outperforms baseline methods in terms of Mean Square Error for imputation and prediction tasks, as well as accuracy in downstream classification task.
- Top Cited Papers
- 15 September 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 8 (18) , 13849-13875
A Survey of Recent Advances in Edge-Computing-Powered Artificial Intelligence of Things
The Internet of Things (IoT) has created a ubiquitously connected world powered by a multitude of wired and wireless sensors generating a variety of heterogeneous data over time in a myriad of fields and applications. To extract complete information from these data, advanced artificial intelligence (AI) technology, especially deep learning (DL), has proved successful in facilitating data analytics, future prediction and decision making. The collective integration of AI and the IoT has greatly promoted the rapid development of AI-of-Things (AIoT) systems that analyze and respond to external stimuli more intelligently without involvement by humans. However, it is challenging or infeasible to process massive amounts of data in the cloud due to the destructive impact of the volume, velocity, and veracity of data and fatal transmission latency on networking infrastructures. These critical challenges can be adequately addressed by introducing edge computing. This article conducts an extensive survey of an end-edge-cloud orchestrated architecture for flexible AIoT systems. Specifically, it begins with articulating fundamental concepts including the IoT, AI and edge computing. Guided by these concepts, it explores the general AIoT architecture, presents a practical AIoT example to illustrate how AI can be applied in real-world applications and summarizes promising AIoT applications. Then, the emerging technologies for AI models regarding inference and training at the edge of the network are reviewed. Finally, the open challenges and future directions in this promising area are outlined.
- 15 September 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 8 (18) , 13849-13875
Top Cited PapersA Survey of Recent Advances in Edge-Computing-Powered Artificial Intelligence of Things
The Internet of Things (IoT) has created a ubiquitously connected world powered by a multitude of wired and wireless sensors generating a variety of heterogeneous data over time in a myriad of fields and applications. To extract complete information from these data, advanced artificial intelligence (AI) technology, especially deep learning (DL), has proved successful in facilitating data analytics, future prediction and decision making. The collective integration of AI and the IoT has greatly promoted the rapid development of AI-of-Things (AIoT) systems that analyze and respond to external stimuli more intelligently without involvement by humans. However, it is challenging or infeasible to process massive amounts of data in the cloud due to the destructive impact of the volume, velocity, and veracity of data and fatal transmission latency on networking infrastructures. These critical challenges can be adequately addressed by introducing edge computing. This article conducts an extensive survey of an end-edge-cloud orchestrated architecture for flexible AIoT systems. Specifically, it begins with articulating fundamental concepts including the IoT, AI and edge computing. Guided by these concepts, it explores the general AIoT architecture, presents a practical AIoT example to illustrate how AI can be applied in real-world applications and summarizes promising AIoT applications. Then, the emerging technologies for AI models regarding inference and training at the edge of the network are reviewed. Finally, the open challenges and future directions in this promising area are outlined.