RPRuimin Peng

Ruimin Peng

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Ruimin Peng has a total of 23 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Multi-Branch Mutual-Distillation Transformer for EEG-Based Seizure Subtype Classification

    by Ruimin Peng, Zhenbang Du, Changming Zhao, Jingwei Luo, Wenzhong Liu, Xinxing Chen, Dongrui Wu

    Cross-subject electroencephalogram (EEG) based seizure subtype classification is very important in precise epilepsy diagnostics. Deep learning is a promising solution, due to its ability to automatically extract latent patterns. However, it usually requires a large amount of training data, which may not always be available in clinical practice. This paper proposes Multi-Branch Mutual-Distillation (MBMD) Transformer for cross-subject EEG-based seizure subtype classification, which can be effectively trained from small labeled data. MBMD Transformer replaces all even-numbered encoder blocks of the vanilla Vision Transformer by our designed multi-branch encoder blocks. A mutual-distillation strategy is proposed to transfer knowledge between the raw EEG data and its wavelets of different frequency bands. Experiments on two public EEG datasets demonstrated that our proposed MBMD Transformer outperformed several traditional machine learning and state-of-the-art deep learning approaches. To our knowledge, this is the first work on knowledge distillation for EEG-based seizure subtype classification.


  • Open Access

    Mixture of Experts for EEG-Based Seizure Subtype Classification

    by Zhenbang Du, Ruimin Peng, Wenzhong Liu, Wei Li, Dongrui Wu

    Epilepsy is a pervasive neurological disorder affecting approximately 50 million individuals worldwide. Electroencephalogram (EEG) based seizure subtype classification plays a crucial role in epilepsy diagnosis and treatment. However, automatic seizure subtype classification faces at least two challenges: 1) class imbalance, i.e., certain seizure types are considerably less common than others; and, 2) no a priori knowledge integration, so that a large number of labeled EEG samples are needed to train a machine learning model, particularly, deep learning. This paper proposes two novel Mixture of Experts (MoE) models, Seizure-MoE and Mix-MoE, for EEG-based seizure subtype classification. Particularly, Mix-MoE adequately addresses the above two challenges: 1) It introduces a novel imbalanced sampler to address significant class imbalance; and, 2) It incorporates a priori knowledge of manual EEG features into the deep neural network to improve the classification performance. Experiments on two public datasets demonstrated that the proposed Seizure-MoE and Mix-MoE outperformed multiple existing approaches in cross-subject EEG-based seizure subtype classification. Our proposed MoE models may also be easily extended to other EEG classification problems with severe class imbalance, e.g., sleep stage classification.


  • Bagging and Boosting Fine-Tuning for Ensemble Learning

    by Changming Zhao, Ruimin Peng, Dongrui Wu

    Ensemble learning aggregates outputs from multiple base learners for better performance. Bootstrap aggregating (Bagging) and boosting are two popular such approaches. They are suitable for integrating unstable base learners with large variance and weak base learners with large bias, respectively, but not base learners with small variance and/or bias, e.g., support vector machine, regularized logistic regression and ridge regression. This paper proposes two novel ensemble-learning-based fine-tuning approaches, boosting fine-tuning (BF) and Bagging and boosting fine-tuning (BBF), to fine-tune learners with small variance and/or bias for better performance. BF embeds boosting in a single hidden layer neural network. In each iteration, BF first uses Newton's method to generate a temporary training set, and then trains a boosting learner on it. BBF combines BF and Bagging. It first uses bootstrap to obtain multiple replicas of the training set, and then trains a BF learner on each replica. Extensive experiments on 46 real world datasets demonstrated that BBF is flexible, robust and effective, and can fine-tune many popular classifiers to achieve better generalization performance.


  • Open Access

    Source-Free Domain Adaptation (SFDA) for Privacy-Preserving Seizure Subtype Classification

    by Changming Zhao, Ruimin Peng, Dongrui Wu

    Electroencephalogram (EEG) based seizure subtype classification is very important in clinical diagnostics. Source-free domain adaptation (SFDA) uses a pre-trained source model, instead of the source data, for privacy-preserving transfer learning. SFDA is useful in seizure subtype classification, which can protect the privacy of the source patients, while reducing the amount of labeled calibration data for a new patient. This paper introduces semi-supervised transfer boosting (SS-TrBoosting), a boosting-based SFDA approach for seizure subtype classification. We further extend it to unsupervised transfer boosting (U-TrBoosting) for unsupervised SFDA, i.e., the new patient does not need any labeled EEG data. Experiments on three public seizure datasets demonstrated that SS-TrBoosting and U-TrBoosting outperformed multiple classical and state-of-the-art machine learning approaches in cross-dataset/cross-patient seizure subtype classification.


  • BoostTree and BoostForest for Ensemble Learning

    by Changming Zhao, Dongrui Wu, Jian Huang, Ye Yuan, Hai-Tao Zhang, Ruimin Peng, Zhenhua Shi

    Bootstrap aggregating (Bagging) and boosting are two popular ensemble learning approaches, which combine multiple base learners to generate a composite model for more accurate and more reliable performance. They have been widely used in biology, engineering, healthcare, etc. This paper proposes BoostForest, which is an ensemble learning approach using BoostTree as base learners and can be used for both classification and regression. BoostTree constructs a tree model by gradient boosting. It increases the randomness (diversity) by drawing the cut-points randomly at node splitting. BoostForest further increases the randomness by bootstrapping the training data in constructing different BoostTrees. BoostForest generally outperformed four classical ensemble learning approaches (Random Forest, Extra-Trees, XGBoost and LightGBM) on 35 classification and regression datasets. Remarkably, BoostForest tunes its parameters by simply sampling them randomly from a parameter pool, which can be easily specified, and its ensemble learning framework can also be used to combine many other base learners.


  • Layer Normalization for TSK Fuzzy System Optimization in Regression Problems

    by Yuqi Cui, Yifan Xu, Ruimin Peng, Dongrui Wu

    Recently, mini-batch gradient descent (MBGD) based optimization has become popular in TSK fuzzy system optimization. However, it suffers from some challenges, including the curse of dimensionality and the sensitivity to the choice of the optimizer. The former has been alleviated by our previously proposed high-dimensional TSK (HTSK) algorithm. In this paper, we point out that the latter is caused by the gradient vanishing problem on the rule consequent parameters, which in turn is caused by the small magnitude of the normalized rule firing levels, especially when the number of rules is large. Thus, the rule consequents are easily trapped into a bad local minimum with poor generalization performance. We propose to use first layer normalization (LN) to amplify the small firing levels, and then rectified linear unit (ReLU) to discard rules far away from the current training sample. We evaluated our proposed HTSK-LN and HTSK-LN-ReLU on twelve regression datasets with various sizes and dimensionalities. Experiments demonstrated that they can significantly improve the generalization performance, regardless of the training set size, feature dimensionality, choice of the optimizer, and rulebase size.


  • Open Access

    TIE-EEGNet: Temporal Information Enhanced EEGNet for Seizure Subtype Classification

    by Ruimin Peng, Changming Zhao, Jun Jiang, Guangtao Kuang, Yuqi Cui, Yifan Xu, Hao Du, Jianbo Shao, Dongrui Wu

    Electroencephalogram (EEG) based seizure subtype classification is very important in clinical diagnostics. However, manual seizure subtype classification is expensive and time-consuming, whereas automatic classification usually needs a large number of labeled samples for model training. This paper proposes an EEGNet-based slim deep neural network, which relieves the labeled data requirement in EEG-based seizure subtype classification. A temporal information enhancement module with sinusoidal encoding is used to augment the first convolution layer of EEGNet. A training strategy for automatic hyper-parameter selection is also proposed. Experiments on the public TUSZ dataset and our own CHSZ dataset with infants and children demonstrated that our proposed TIE-EEGNet outperformed several traditional and deep learning models in cross-subject seizure subtype classification. Additionally, it also achieved the best performance in a challenging transfer learning scenario. Both our code and the CHSZ dataset are publicized.


  • Open Access

    Transfer Learning for Motor Imagery Based Brain-Computer Interfaces: A Complete Pipeline

    by Dongrui Wu, Xue Jiang, Ruimin Peng, Wanzeng Kong, Jian Huang, Zhigang Zeng

    Transfer learning (TL) has been widely used in motor imagery (MI) based brain-computer interfaces (BCIs) to reduce the calibration effort for a new subject, and demonstrated promising performance. While a closed-loop MI-based BCI system, after electroencephalogram (EEG) signal acquisition and temporal filtering, includes spatial filtering, feature engineering, and classification blocks before sending out the control signal to an external device, previous approaches only considered TL in one or two such components. This paper proposes that TL could be considered in all three components (spatial filtering, feature engineering, and classification) of MI-based BCIs. Furthermore, it is also very important to specifically add a data alignment component before spatial filtering to make the data from different subjects more consistent, and hence to facilitate subsequential TL. Offline calibration experiments on two MI datasets verified our proposal. Especially, integrating data alignment and sophisticated TL approaches can significantly improve the classification performance, and hence greatly reduces the calibration effort.