Shubo Liu
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
Shubo Liu has a total of 73 co-authors. Here are the top co-authors by number of shared publications:
Zhaohui Cai
Wuhan University
8 shared publications- Zhaohui Cai
School of Computer Science, Wuhan University, Wuhan, China
8 shared publications - Jun Wang
South-Central Minzu University
7 shared publications Guoqing Tu
Wuhan University
6 shared publicationsDan Li
School of Computer Science, Wuhan University, Wuhan 430072, China
5 shared publications- Guoqing Tu
School of Cyber Science and Engineering, Wuhan University, Wuhan, China
5 shared publications
Latest Publications
- 14 July 2026
- Published by Springer Nature
- p. 117-128
DP-OKM: An Efficient Dual-Phase Online Clustering Framework for Resource-Constrained Edge Gateways
- 14 July 2026
- Published by Springer Nature
- p. 117-128
DP-OKM: An Efficient Dual-Phase Online Clustering Framework for Resource-Constrained Edge Gateways
- Open Access
- 24 September 2025
- Published by Springer Nature in Journal of King Saud University Computer and Information Sciences
- Vol. 37 (8) , 1-20
PLZW: FPGA-based Pipelined LZW for lossless compression of edge data
The rapid growth of IoT devices and data in edge computing applications has created a pressing need for efficient lossless compression of end-edge data. The Lempel-Ziv-Welch (LZW) algorithm, widely used in these scenarios, faces bottlenecks in compression speed due to its inherent data dependency. Unlike existing multi-cycle architectures, we propose PLZW, a pipeline-based LZW acceleration architecture with three novel mechanisms: a data bypass mechanism that allows data to pass directly between pipeline stages, minimizing stalls; a multi-level caching mechanism to reduce pipeline stalls caused by long dictionary update times; and a hash prediction mechanism to improve dictionary lookup hit rates and reduce stall frequency. Our field-programmable gate array (FPGA) implementation demonstrates a 2.5 $$\times $$ speedup over existing state-of-the-art methods while maintaining competitive power consumption, resource utilization, and compression ratio. Furthermore, the resource utilization remains below 1% of total FPGA resources, and the proposed mechanisms improve the dictionary first-hit rate by 35.8%. This work offers a high-speed, lightweight, generic solution for lossless compression of end-edge data. PLZW provides a reference implementation for optimizing hardware-based data compression in real-time and resource-constrained applications.- 24 September 2025
- Published by Springer Nature in Journal of King Saud University Computer and Information Sciences
- Vol. 37 (8) , 1-20
Open AccessPLZW: FPGA-based Pipelined LZW for lossless compression of edge data
The rapid growth of IoT devices and data in edge computing applications has created a pressing need for efficient lossless compression of end-edge data. The Lempel-Ziv-Welch (LZW) algorithm, widely used in these scenarios, faces bottlenecks in compression speed due to its inherent data dependency. Unlike existing multi-cycle architectures, we propose PLZW, a pipeline-based LZW acceleration architecture with three novel mechanisms: a data bypass mechanism that allows data to pass directly between pipeline stages, minimizing stalls; a multi-level caching mechanism to reduce pipeline stalls caused by long dictionary update times; and a hash prediction mechanism to improve dictionary lookup hit rates and reduce stall frequency. Our field-programmable gate array (FPGA) implementation demonstrates a 2.5 $$\times $$ speedup over existing state-of-the-art methods while maintaining competitive power consumption, resource utilization, and compression ratio. Furthermore, the resource utilization remains below 1% of total FPGA resources, and the proposed mechanisms improve the dictionary first-hit rate by 35.8%. This work offers a high-speed, lightweight, generic solution for lossless compression of end-edge data. PLZW provides a reference implementation for optimizing hardware-based data compression in real-time and resource-constrained applications. - 26 July 2025
- Published by Springer Nature
- p. 173-184
STMDLinear: An Efficient Network for Industrial Serial Communication PHM
- 26 July 2025
- Published by Springer Nature
- p. 173-184
STMDLinear: An Efficient Network for Industrial Serial Communication PHM
- Open Access
- 11 April 2025
- Published by Association for the Advancement of Artificial Intelligence (AAAI) in Proceedings of the AAAI Conference on Artificial Intelligence
- Vol. 39 (20) , 21833-21841
Revisiting Interpolation for Noisy Label Correction
Label correction methods are popular for their simple architecture in learning with noisy labels. However, they suffer severely from false label correction and achieve subpar performance compared with state-of-the-art methods. In this paper, we revisit the label correction methods through theoretical analysis of gradient scaling and demonstrate that the sample-wise dynamic and class-wise uniformity of interpolation weight prevents memorization of the mislabeled samples. We then propose DULC, a simple yet effective label correction method that uses the normalized Jensen-Shannon divergence (JSD) metric as the interpolation weight to promote sample-wise dynamic and class-wise uniformity. Additionally, we provide theoretical evidence that sharpening predictions in label correction facilitates the memorization of true class, and we achieve it by employing the augmentation strategy along with the sharpening function. Extensive experiments on CIFAR-10, CIFAR-100, TinyImageNet, WebVision and Clothing1M datasets demonstrate substantial improvements over state-of-the-art methods.
- 11 April 2025
- Published by Association for the Advancement of Artificial Intelligence (AAAI) in Proceedings of the AAAI Conference on Artificial Intelligence
- Vol. 39 (20) , 21833-21841
Open AccessRevisiting Interpolation for Noisy Label Correction
Label correction methods are popular for their simple architecture in learning with noisy labels. However, they suffer severely from false label correction and achieve subpar performance compared with state-of-the-art methods. In this paper, we revisit the label correction methods through theoretical analysis of gradient scaling and demonstrate that the sample-wise dynamic and class-wise uniformity of interpolation weight prevents memorization of the mislabeled samples. We then propose DULC, a simple yet effective label correction method that uses the normalized Jensen-Shannon divergence (JSD) metric as the interpolation weight to promote sample-wise dynamic and class-wise uniformity. Additionally, we provide theoretical evidence that sharpening predictions in label correction facilitates the memorization of true class, and we achieve it by employing the augmentation strategy along with the sharpening function. Extensive experiments on CIFAR-10, CIFAR-100, TinyImageNet, WebVision and Clothing1M datasets demonstrate substantial improvements over state-of-the-art methods.
- 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
- Top Cited PapersOpen Access
- 1 October 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 15338-15348
AerialVLN: Vision-and-Language Navigation for UAVs
Recently emerged Vision-and-Language Navigation (VLN) tasks have drawn significant attention in both computer vision and natural language processing communities. Existing VLN tasks are built for agents that navigate on the ground, either indoors or outdoors. However, many tasks require intelligent agents to carry out in the sky, such as UAV-based goods delivery, traffic/security patrol, and scenery tour, to name a few. Navigating in the sky is more complicated than on the ground because agents need to consider the flying height and more complex spatial relationship reasoning. To fill this gap and facilitate research in this field, we propose a new task named AerialVLN, which is UAV-based and towards outdoor environments. We develop a 3D simulator rendered by near-realistic pictures of 25 city-level scenarios. Our simulator supports continuous navigation, environment extension and configuration. We also proposed an extended baseline model based on the widely-used cross-modal-alignment (CMA) navigation methods. We find that there is still a significant gap between the baseline model and human performance, which suggests AerialVLN is a new challenging task. Dataset and code is available at https://github.com/AirVLN/AirVLN.
- 1 October 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 15338-15348
Top Cited PapersOpen AccessAerialVLN: Vision-and-Language Navigation for UAVs
Recently emerged Vision-and-Language Navigation (VLN) tasks have drawn significant attention in both computer vision and natural language processing communities. Existing VLN tasks are built for agents that navigate on the ground, either indoors or outdoors. However, many tasks require intelligent agents to carry out in the sky, such as UAV-based goods delivery, traffic/security patrol, and scenery tour, to name a few. Navigating in the sky is more complicated than on the ground because agents need to consider the flying height and more complex spatial relationship reasoning. To fill this gap and facilitate research in this field, we propose a new task named AerialVLN, which is UAV-based and towards outdoor environments. We develop a 3D simulator rendered by near-realistic pictures of 25 city-level scenarios. Our simulator supports continuous navigation, environment extension and configuration. We also proposed an extended baseline model based on the widely-used cross-modal-alignment (CMA) navigation methods. We find that there is still a significant gap between the baseline model and human performance, which suggests AerialVLN is a new challenging task. Dataset and code is available at https://github.com/AirVLN/AirVLN.
- 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 July 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 72 (00189456) , 1-16
An Improved Sequence-to-Point Learning for Non-Intrusive Load Monitoring Based on Discrete Wavelet Transform
Nonintrusive load monitoring (NILM) is a process that monitors the aggregated power consumption data of customers measured by a single sensor and decomposes the real-time power consumption of each dedicated device. Recent research has been focused on in-depth learning. However, the expensive cost of training time and the huge model scale are not conducive to the realization of smart meters. It is still challenging to accurately predict the real-time power of high-frequency appliances. This paper uses the discrete wavelet transform (DWT) to preprocess the data, which divides the frequency of the training power data. The processed data will be transferred to the enhanced sequence-to-point network (en-S2P) for training. The en-S2P network is the promotion of a sequence-to-point model (S2P) optimized by the autoencoder and bidirectional long short-term memory (Bi-LSTM) layer. And it is compressed by a combined pruning algorithm after being trained. The proposed model method is tested on the UK-DALE and REDD datasets using db2 and sym5 wavelet transform and compared with the S2P. Extensive experiments show that the proposed model can obtain a more satisfactory decomposition performance of appliances, especially high-frequency. In addition, it has a more lightweight scale and maintains a certain degree of sparsity, which is friendly to electricity meters.
- 18 July 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 72 (00189456) , 1-16
An Improved Sequence-to-Point Learning for Non-Intrusive Load Monitoring Based on Discrete Wavelet Transform
Nonintrusive load monitoring (NILM) is a process that monitors the aggregated power consumption data of customers measured by a single sensor and decomposes the real-time power consumption of each dedicated device. Recent research has been focused on in-depth learning. However, the expensive cost of training time and the huge model scale are not conducive to the realization of smart meters. It is still challenging to accurately predict the real-time power of high-frequency appliances. This paper uses the discrete wavelet transform (DWT) to preprocess the data, which divides the frequency of the training power data. The processed data will be transferred to the enhanced sequence-to-point network (en-S2P) for training. The en-S2P network is the promotion of a sequence-to-point model (S2P) optimized by the autoencoder and bidirectional long short-term memory (Bi-LSTM) layer. And it is compressed by a combined pruning algorithm after being trained. The proposed model method is tested on the UK-DALE and REDD datasets using db2 and sym5 wavelet transform and compared with the S2P. Extensive experiments show that the proposed model can obtain a more satisfactory decomposition performance of appliances, especially high-frequency. In addition, it has a more lightweight scale and maintains a certain degree of sparsity, which is friendly to electricity meters.
- Open Access
- 28 June 2023
- Published by MDPI AG in Algorithms
- Vol. 16 (7) , 317
Audio Anti-Spoofing Based on Audio Feature Fusion
The rapid development of speech synthesis technology has significantly improved the naturalness and human-likeness of synthetic speech. As the technical barriers for speech synthesis are rapidly lowering, the number of illegal activities such as fraud and extortion is increasing, posing a significant threat to authentication systems, such as automatic speaker verification. This paper proposes an end-to-end speech synthesis detection model based on audio feature fusion in response to the constantly evolving synthesis techniques and to improve the accuracy of detecting synthetic speech. The model uses a pre-trained wav2vec2 model to extract features from raw waveforms and utilizes an audio feature fusion module for back-end classification. The audio feature fusion module aims to improve the model accuracy by adequately utilizing the audio features extracted from the front end and fusing the information from timeframes and feature dimensions. Data augmentation techniques are also used to enhance the performance generalization of the model. The model is trained on the training and development sets of the logical access (LA) dataset of the ASVspoof 2019 Challenge, an international standard, and is tested on the logical access (LA) and deep-fake (DF) evaluation datasets of the ASVspoof 2021 Challenge. The equal error rate (EER) on ASVspoof 2021 LA and ASVspoof 2021 DF are 1.18% and 2.62%, respectively, achieving the best results on the DF dataset.
- 28 June 2023
- Published by MDPI AG in Algorithms
- Vol. 16 (7) , 317
Open AccessAudio Anti-Spoofing Based on Audio Feature Fusion
The rapid development of speech synthesis technology has significantly improved the naturalness and human-likeness of synthetic speech. As the technical barriers for speech synthesis are rapidly lowering, the number of illegal activities such as fraud and extortion is increasing, posing a significant threat to authentication systems, such as automatic speaker verification. This paper proposes an end-to-end speech synthesis detection model based on audio feature fusion in response to the constantly evolving synthesis techniques and to improve the accuracy of detecting synthetic speech. The model uses a pre-trained wav2vec2 model to extract features from raw waveforms and utilizes an audio feature fusion module for back-end classification. The audio feature fusion module aims to improve the model accuracy by adequately utilizing the audio features extracted from the front end and fusing the information from timeframes and feature dimensions. Data augmentation techniques are also used to enhance the performance generalization of the model. The model is trained on the training and development sets of the logical access (LA) dataset of the ASVspoof 2019 Challenge, an international standard, and is tested on the logical access (LA) and deep-fake (DF) evaluation datasets of the ASVspoof 2021 Challenge. The equal error rate (EER) on ASVspoof 2021 LA and ASVspoof 2021 DF are 1.18% and 2.62%, respectively, achieving the best results on the DF dataset.