Changchun He
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Changchun He has a total of 14 co-authors. Here are the top co-authors by number of shared publications:
- Xin Huo
Harbin Institute of Technology
14 shared publications - Baohan Mi
Harbin Institute of Technology
6 shared publications Chao Zhu
Shanghai Rising Digital Company Ltd., Shanghai, China
6 shared publications- Hewei Gao
Control and simulation center, Harbin Institute of Technology, Harbin, China
4 shared publications - Chentao Liu
Harbin Institute of Technology
3 shared publications - Songlin Chen
Harbin Institute of Technology
3 shared publications
Latest Publications
- 16 September 2026
- Published by Elsevier in Knowledge-Based Systems
- Vol. 352
Shapeleter: Shapelet enhancer via multiview positional embedding for time series classification and extrinsic regression
- 16 September 2026
- Published by Elsevier in Knowledge-Based Systems
- Vol. 352
Shapeleter: Shapelet enhancer via multiview positional embedding for time series classification and extrinsic regression
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks and Learning Systems
- Vol. PP, 1-14
Multipatch Augmentation Learning Based on Dual-Policy Model for Time Series Classification
Multiple instance learning (MIL)-based time series classification (TSC) predicts instance-level labels and aggregates them to derive bag-level labels; however, this approach encounters instability as anomalous instances significantly impact the bag-level label predictions. Although well-chosen series transformations and patch lengths improve instance discriminability and stability, determining appropriate configurations remains challenging. To address this, a dual-policy model is adopted to adaptively select a suitable transformation combination and patch length from a predefined transformation space according to the preference distribution of the training set. Building on this, a novel TSC algorithm, multipatch augmentation learning based on dual-policy model (MPAL-DPM), is proposed. MPAL-DPM is trained in two stages and comprises three functional modules. First, the policy model determines a transformation combination, encoded with Gray codes that assign adjacent values to combinations differing by a single transformation and thereby promote smooth policy optimization. This combination drives policy series augmentation, emphasizing subtle yet significant variations. Then, a scalable patch fine-tunes the policy-preset patch length to match the augmented data, alleviating the unstable feature extraction caused by uneven information density. Finally, multipatch classification (MPC) extracts features from each patch, weighs the importance of instances, and yields more consistent predictions. Experiments on the UCR archive demonstrate that MPAL-DPM achieves performance comparable to state-of-the-art classifiers, confirming its effectiveness, robustness, and scalability.
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks and Learning Systems
- Vol. PP, 1-14
Multipatch Augmentation Learning Based on Dual-Policy Model for Time Series Classification
Multiple instance learning (MIL)-based time series classification (TSC) predicts instance-level labels and aggregates them to derive bag-level labels; however, this approach encounters instability as anomalous instances significantly impact the bag-level label predictions. Although well-chosen series transformations and patch lengths improve instance discriminability and stability, determining appropriate configurations remains challenging. To address this, a dual-policy model is adopted to adaptively select a suitable transformation combination and patch length from a predefined transformation space according to the preference distribution of the training set. Building on this, a novel TSC algorithm, multipatch augmentation learning based on dual-policy model (MPAL-DPM), is proposed. MPAL-DPM is trained in two stages and comprises three functional modules. First, the policy model determines a transformation combination, encoded with Gray codes that assign adjacent values to combinations differing by a single transformation and thereby promote smooth policy optimization. This combination drives policy series augmentation, emphasizing subtle yet significant variations. Then, a scalable patch fine-tunes the policy-preset patch length to match the augmented data, alleviating the unstable feature extraction caused by uneven information density. Finally, multipatch classification (MPC) extracts features from each patch, weighs the importance of instances, and yields more consistent predictions. Experiments on the UCR archive demonstrate that MPAL-DPM achieves performance comparable to state-of-the-art classifiers, confirming its effectiveness, robustness, and scalability.
- 4 November 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Journal
- Vol. 25 (24) , 44428-44437
Unsupervised Feature Selection-Based Interval Enhancement for Time Series Clustering and Its Application
The proliferation of sensor-generated data necessitates robust time series clustering (TSCL) methods that effectively capture features and perceive multiscale patterns. Thus, in this article, an unsupervised feature selection-based interval enhancement (UFS-IE) algorithm is proposed for TSCL tasks, incorporating two core components. In the IE phase, three types of features, quantile, interquartile range (IQR), and skewness, are extracted across multiscale intervals to enhance variety. To diversify interval representation, an adaptive wavelet basis selection method for discrete wavelet transforms (DWTs) is developed, guided by the principle of maximum information and minimum redundancy (MIMR). With the objective of mitigating feature redundancy and promoting discriminative power, an unsupervised feature filter is introduced by modifying Laplacian scoring through cosine similarity-driven weighting, coupled with a dual-threshold mechanism for optimal feature retention based on intrinsic variance distribution. The superiority of UFS-IE is demonstrated via experiments on 112 UCR datasets, achieving an average clustering accuracy of 54.78%, and its industrial applicability is further validated by an application case on the excavator sensor dataset, where the maximum fault diagnosis accuracy reaches 71.52%.
- 4 November 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Journal
- Vol. 25 (24) , 44428-44437
Unsupervised Feature Selection-Based Interval Enhancement for Time Series Clustering and Its Application
The proliferation of sensor-generated data necessitates robust time series clustering (TSCL) methods that effectively capture features and perceive multiscale patterns. Thus, in this article, an unsupervised feature selection-based interval enhancement (UFS-IE) algorithm is proposed for TSCL tasks, incorporating two core components. In the IE phase, three types of features, quantile, interquartile range (IQR), and skewness, are extracted across multiscale intervals to enhance variety. To diversify interval representation, an adaptive wavelet basis selection method for discrete wavelet transforms (DWTs) is developed, guided by the principle of maximum information and minimum redundancy (MIMR). With the objective of mitigating feature redundancy and promoting discriminative power, an unsupervised feature filter is introduced by modifying Laplacian scoring through cosine similarity-driven weighting, coupled with a dual-threshold mechanism for optimal feature retention based on intrinsic variance distribution. The superiority of UFS-IE is demonstrated via experiments on 112 UCR datasets, achieving an average clustering accuracy of 54.78%, and its industrial applicability is further validated by an application case on the excavator sensor dataset, where the maximum fault diagnosis accuracy reaches 71.52%.
- 3 July 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems I: Regular Papers
- Vol. 72 (12) , 7874-7887
Mecha: Multiview Enhanced Characteristics via Series Shuffling for Time Series Classification and Its Application to Turntable Circuit
In various electronic circuits with privacy and security constraints, only a single status monitoring signal is obtained, which renders domain knowledge inapplicable. To address this challenge, the data-driven univariate time series classification (TSC) method is a suitable and effective solution for diagnosing the system’s fault type. The current feature-based TSC method is interpretable by extracting a descriptive statistics-based feature collection, but its TSC performance is limited due to poor extensibility and feature redundancy. Therefore, in this paper, a novel and extensible feature-based TSC algorithm with ensemble structure and enhancement framework Multiview Enhanced Characteristics (Mecha) is proposed, which consists of three components. In the diverse feature extractor, the global and local patterns are enhanced via shuffling mapping with dilation and interleaving mechanisms, improving the feature diversity and expressiveness. In the ensemble feature selector, diverse and stable multiview features are adaptively generated by multiple filters and intersections based on the feature stability and diversity scores. In the heterogeneous ensemble classifier, the ridge regression with cross-validation and extremely randomized trees classifiers are integrated via hard voting to enhance classifier diversity. Finally, the state-of-the-art feature-based TSC performance and application effectiveness of the proposed Mecha without domain knowledge is verified on public UCR datasets and a practical turntable current dataset.
- 3 July 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems I: Regular Papers
- Vol. 72 (12) , 7874-7887
Mecha: Multiview Enhanced Characteristics via Series Shuffling for Time Series Classification and Its Application to Turntable Circuit
In various electronic circuits with privacy and security constraints, only a single status monitoring signal is obtained, which renders domain knowledge inapplicable. To address this challenge, the data-driven univariate time series classification (TSC) method is a suitable and effective solution for diagnosing the system’s fault type. The current feature-based TSC method is interpretable by extracting a descriptive statistics-based feature collection, but its TSC performance is limited due to poor extensibility and feature redundancy. Therefore, in this paper, a novel and extensible feature-based TSC algorithm with ensemble structure and enhancement framework Multiview Enhanced Characteristics (Mecha) is proposed, which consists of three components. In the diverse feature extractor, the global and local patterns are enhanced via shuffling mapping with dilation and interleaving mechanisms, improving the feature diversity and expressiveness. In the ensemble feature selector, diverse and stable multiview features are adaptively generated by multiple filters and intersections based on the feature stability and diversity scores. In the heterogeneous ensemble classifier, the ridge regression with cross-validation and extremely randomized trees classifiers are integrated via hard voting to enhance classifier diversity. Finally, the state-of-the-art feature-based TSC performance and application effectiveness of the proposed Mecha without domain knowledge is verified on public UCR datasets and a practical turntable current dataset.
- 13 May 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Industrial Informatics
- Vol. 21 (8) , 6188-6197
A DTW-Gaussian Spatiotemporal Self-Attention Network and Its Application in Industrial Fault Diagnosis With Unequal-Length Sensor Data
Equipment operating in intermittent industrial processes generates complex system coupling and unequal-length sensor data, which are considered significant challenges for fault diagnosis in industrial production. To address these challenges, a generic fault diagnosis approach, the dynamic time warping Gaussian spatiotemporal self-attention network (DGSSANet), is proposed. dynamic time warping combined with Gaussian blur is employed to handle sensor signal complexity, transforming unequal-length data into warping matrices of equal dimensions. The inclusion of spatiotemporal self-attention, with the multiscale temporal attention module and multielement spatial self-attention module, enhances the ability of DGSSANet to capture spatial and temporal relationships. DGSSANet is validated through benchmark experiments on bearing datasets and applied to excavator cases, with its interpretability analyzed via visualization. The results demonstrate that DGSSANet addresses the challenges of fault diagnosis in intermittent production processes effectively.
- 13 May 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Industrial Informatics
- Vol. 21 (8) , 6188-6197
A DTW-Gaussian Spatiotemporal Self-Attention Network and Its Application in Industrial Fault Diagnosis With Unequal-Length Sensor Data
Equipment operating in intermittent industrial processes generates complex system coupling and unequal-length sensor data, which are considered significant challenges for fault diagnosis in industrial production. To address these challenges, a generic fault diagnosis approach, the dynamic time warping Gaussian spatiotemporal self-attention network (DGSSANet), is proposed. dynamic time warping combined with Gaussian blur is employed to handle sensor signal complexity, transforming unequal-length data into warping matrices of equal dimensions. The inclusion of spatiotemporal self-attention, with the multiscale temporal attention module and multielement spatial self-attention module, enhances the ability of DGSSANet to capture spatial and temporal relationships. DGSSANet is validated through benchmark experiments on bearing datasets and applied to excavator cases, with its interpretability analyzed via visualization. The results demonstrate that DGSSANet addresses the challenges of fault diagnosis in intermittent production processes effectively.
- 25 March 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Systems, Man, and Cybernetics: Systems
- Vol. 55 (6) , 4052-4063
Multichannel-Based Multiview Shallow Fusion for Time Series Classification and Its Application in Fault Diagnosis
In the current time series classification (TSC) field, shallow concatenation, deep fusion, and hybrid ensemble multichannel frameworks (MCF) represented by convolution-based, deep learning, and hybrid methods have achieved competitive TSC performance. However, the massive kernels, deep fusion, and heterogeneous ensemble mechanisms, which are the core of the three frameworks, respectively, lead to overfitting risks. Therefore, in this article, a novel convolution-based TSC algorithm multichannel-based multiview shallow fusion (MC-MSF) within a new shallow fusion ensemble-based MCF is proposed. MC-MSF enhances feature diversity, quality, and classifier diversity while suppressing the overfitting risks via three shallow components. For feature diversity, the original series is mapped to the connected multichannel series spaces, and then diverse pooling features are extracted via a single-layer convolution with fewer kernels. For feature quality, the power of proportion of positive values (PPPV) features with adaptive powers are extracted based on alternating gradient descent, and the multiview shallow feature fusion is implemented to generate fused features. For classifier diversity, diverse linear classifiers are trained on the combined multiview feature vectors to ensemble homogeneously. The state-of-the-art TSC accuracy is achieved by MC-MSF via the sequential operation of three effective shallow components, as verified by comparative experiments on the public UCR and real excavator fault diagnosis application datasets.
- 25 March 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Systems, Man, and Cybernetics: Systems
- Vol. 55 (6) , 4052-4063
Multichannel-Based Multiview Shallow Fusion for Time Series Classification and Its Application in Fault Diagnosis
In the current time series classification (TSC) field, shallow concatenation, deep fusion, and hybrid ensemble multichannel frameworks (MCF) represented by convolution-based, deep learning, and hybrid methods have achieved competitive TSC performance. However, the massive kernels, deep fusion, and heterogeneous ensemble mechanisms, which are the core of the three frameworks, respectively, lead to overfitting risks. Therefore, in this article, a novel convolution-based TSC algorithm multichannel-based multiview shallow fusion (MC-MSF) within a new shallow fusion ensemble-based MCF is proposed. MC-MSF enhances feature diversity, quality, and classifier diversity while suppressing the overfitting risks via three shallow components. For feature diversity, the original series is mapped to the connected multichannel series spaces, and then diverse pooling features are extracted via a single-layer convolution with fewer kernels. For feature quality, the power of proportion of positive values (PPPV) features with adaptive powers are extracted based on alternating gradient descent, and the multiview shallow feature fusion is implemented to generate fused features. For classifier diversity, diverse linear classifiers are trained on the combined multiview feature vectors to ensemble homogeneously. The state-of-the-art TSC accuracy is achieved by MC-MSF via the sequential operation of three effective shallow components, as verified by comparative experiments on the public UCR and real excavator fault diagnosis application datasets.