Electroencephalogram (EEG)-based seizure sub-type classification enhances clinical diagnosis efficiency. Source-free semi-supervised domain adaptation (SF-SSDA), which transfers a pre-trained model to a new dataset with no source data and limited labeled target data, can be used for privacy-preserving seizure subtype classification. This paper considers two challenges in SF-SSDA for EEG-based seizure subtype classification: 1) How to effectively fuse both raw EEG data and expert knowledge in classifier design? 2) How to align the source and target domain distributions for SF-SSDA? We propose a Knowledge-Data Fusion based SF-SSDA approach, KDF-MutuaISHOT, for EEG-based seizure subtype classification. In source model training, KDF uses Jensen-Shannon Diver-gence to facilitate mutual learning between a feature-driven Decision Tree-based model and a data-driven Transformer-based model. To adapt KDF to a new target dataset, an SF-SSDA algorithm, MutualSHOT, is developed, which features a consistency-based pseudo-label selection strategy. Experiments on the public TUSZ and CHSZ datasets demonstrated that KDF-MutualSHOT outperformed other supervised and source-free domain adaptation approaches in cross-subject seizure subtype classification.

The modern cloud computing system has evolved into a highly dynamic and complex ecosystem with thousands of modules. Modifications and updates to these modules occur every day to accommodate customer needs. Unfortunately, these frequent changes may introduce anomalies to the system, whose diffusion can undermine the system performance and even cause system outage. Though very important, it is challenging to detect anomalies at the early stages and locate their root causes, due to the complexity of the cloud ecosystem and the huge number of attribute combinations. This paper proposes DARC for high-dimensional diffusing anomaly detection and root cause location in cloud computing systems. DARC uses first two-stage percentile analysis and Mann-Kendall score thresholding to detect rare anomalies, and then a bottom-up search strategy with three computational complexity reduction techniques to efficiently locate the root causes. Extensive experiments showed that DARC is able to accurately and efficiently locate root causes of diffusing anomalies. It has been successfully used in the daily practice of Alibaba Cloud, one of the world’s largest cloud computing service providers.

Electroencephalogram (EEG) based seizure subtype classification plays an important role in clinical diagnostics. However, existing deep learning approaches face two challenges in such applications: 1) convolutional or recurrent neural network based models have difficulty learning long-term dependencies; and, 2) there are not enough labeled seizure sub-type data for training such models. This paper proposes a Transformer-based self-supervised learning model for EEG-based seizure subtype classification, which copes well with these two challenges. Filter bank analysis is first employed to improve Vision Transformer as a Wavelet Transformer (WaT) encoder, which generates multi-grained feature representations of EEG signals. Then, self-supervised learning is used to pre-train WaT from unlabeled EEG data. Experiments on two public datasets demonstrated that Wavelet2Vec outperformed several other supervised and self-supervised models in cross-subject seizure subtype classification.

Emotion recognition is an important part of affective computing. Utilizing information from multiple modalities would facilitate more accurate emotion recognition. The performance of data-driven machine learning models usually relies on a large amount of labeled training data. However, labeling emotional data is expensive, because each sample usually requires multiple evaluators to annotate. To alleviate the annotation cost, this paper proposes a cross-modal diversity measure that considers the correlation between different modalities and integrates it with the representativeness for sample selection in unsupervised active learning (AL) for regression. To our knowledge, this challenging multi-modal unsupervised AL scenario has not been explored before: previous research only considered either unsupervised uni-modal AL or supervised multi-modal AL. Experiments on RECOLA and IEMOCAP datasets demonstrated the effectiveness of our proposed AL approach.

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 article 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.

Recently, mini-batch gradient descent (MBGD)-based optimization has become popular in Takagi–Sugeno–Kang (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 article, 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.