Transductive domain adaptive learning for epileptic electroencephalogram recognition

Cluster Embedding Joint-Probability-Discrepancy Transfer for Cross-Subject Seizure Detection

Transfer learning (TL) has been applied in seizure detection to deal with differences between different subjects or tasks. In this paper, we consider cross-subject seizure detection that does not rely on patient history records, that is, acquiring knowledge from other subjects through TL to improve seizure detection performance. We propose a novel domain adaptation method, named the Cluster Embedding Joint-Probability-Discrepancy Transfer (CEJT), for data distribution structure learning. Specifically, 1) The joint probability distribution discrepancy is minimized to reduce the distribution shift in the source and target domains, and strengthen the discriminative knowledge of classes. 2) A clustering is performed on the target domain, and the class centroids of sources is used as the clustering prototype of the target domain to enhance data structure. It is worth noting that the manifold regularization is used to improve the quality of clustering prototypes. In addition, a correlation-alignment-based source selection metric (SSC) is designed for most favorable subject selection, reducing the computational cost as well as avoiding some negative transfer. Experiments on 15 patients with focal epilepsy from the Children's Hospital, Zhejiang University School of Medicine (CHZU) database shown that CEJT outperforms several state-of-the-art approaches, and can promote the application of seizure detection.

Role of Ensemble Deep Learning for Brain Tumor Classification in Multiple Magnetic Resonance Imaging Sequence Data

The biopsy is a gold standard method for tumor grading. However, due to its invasive nature, it has sometimes proved fatal for brain tumor patients. As a result, a non-invasive computer-aided diagnosis (CAD) tool is required. Recently, many magnetic resonance imaging (MRI)-based CAD tools have been proposed for brain tumor grading. The MRI has several sequences, which can express tumor structure in different ways. However, a suitable MRI sequence for brain tumor classification is not yet known. The most common brain tumor is 'glioma', which is the most fatal form. Therefore, in the proposed study, to maximize the classification ability between low-grade versus high-grade glioma, three datasets were designed comprising three MRI sequences: T1-Weighted (T1W), T2-weighted (T2W), and fluid-attenuated inversion recovery (FLAIR). Further, five well-established convolutional neural networks, AlexNet, VGG16, ResNet18, GoogleNet, and ResNet50 were adopted for tumor classification. An ensemble algorithm was proposed using the majority vote of above five deep learning (DL) models to produce more consistent and improved results than any individual model. Five-fold cross validation (K5-CV) protocol was adopted for training and testing. For the proposed ensembled classifier with K5-CV, the highest test accuracies of 98.88 ± 0.63%, 97.98 ± 0.86%, and 94.75 ± 0.61% were achieved for FLAIR, T2W, and T1W-MRI data, respectively. FLAIR-MRI data was found to be most significant for brain tumor classification, where it showed a 4.17% and 0.91% improvement in accuracy against the T1W-MRI and T2W-MRI sequence data, respectively. The proposed ensembled algorithm (MajVot) showed significant improvements in the average accuracy of three datasets of 3.60%, 2.84%, 1.64%, 4.27%, and 1.14%, respectively, against AlexNet, VGG16, ResNet18, GoogleNet, and ResNet50.

Mutual Supervised Fusion & Transfer Learning with Interpretable Linguistic Meaning for Social Data Analytics

Social data analytics is often taken as the most commonly used method for community discovery, product recommendations, knowledge graph, etc. In this study, social data are firstly represented in different feature spaces by using various feature extraction algorithms. Then we build a transfer learning model to leverage knowledge from multiple feature spaces. During modeling, since the assumption that the training and the testing data have the same distribution is always true, we give a theorem and its proof which asserts the necessary and sufficient condition for achieving a minimum testing error. We also theoretically demonstrate that maximizing the classification error consistency across different feature spaces can improve the classification performance. Additionally, the cluster assumption derived from semi-supervised learning is introduced to enhance knowledge transfer. Finally, a Tagaki-Sugeno-Kang (TSK) fuzzy system-based learning algorithm is proposed, which can generate interpretable fuzzy rules. Experimental results not only demonstrate the promising social data classification performance of our proposed approach but also show its interpretability which is missing in many other models.

Online Prediction of Lead Seizures from iEEG Data

We describe a novel system for online prediction of lead seizures from long-term intracranial electroencephalogram (iEEG) recordings for canines with naturally occurring epilepsy. This study adopts new specification of lead seizures, reflecting strong clustering of seizures in observed data. This clustering results in fewer lead seizures (~7 lead seizures per dog), and hence new challenges for online seizure prediction, that are addressed in the proposed system. In particular, the machine learning part of the system is implemented using the group learning method suitable for modeling sparse and noisy seizure data. In addition, several modifications for the proposed system are introduced to cope with the non-stationarity of a noisy iEEG signal. They include: (1) periodic retraining of the SVM classifier using most recent training data; (2) removing samples with noisy labels from training data; and (3) introducing a new adaptive post-processing technique for combining many predictions made for 20 s windows into a single prediction for a 4 h segment. Application of the proposed system requires only two lead seizures for training the initial model, and results in high prediction performance for all four dogs (with mean 0.84 sensitivity, 0.27 time-in-warning, and 0.78 false-positive rate per day). The proposed system achieves accurate prediction of lead seizures during long-term test periods, 3–16 lead seizures during a 169–364 day test period, whereas earlier studies did not differentiate between lead vs. non-lead seizures and used much shorter test periods (~few days long).

Identification of Epileptic EEG Signals Through TSK Transfer Learning Fuzzy System

We propose a new model to identify epilepsy EEG signals. Some existing intelligent recognition technologies require that the training set and test set have the same distribution when recognizing EEG signals, some only consider reducing the marginal distribution distance of the data while ignoring the intra-class information of data, and some lack of interpretability. To address these deficiencies, we construct a TSK transfer learning fuzzy system (TSK-TL) based on the easy-to-interpret TSK fuzzy system the transfer learning method. The proposed model is interpretable. By using the information contained in the source domain and target domains more effectively, the requirements for data distribution are further relaxed. It realizes the identification of epilepsy EEG signals in data drift scene. The experimental results show that compared with the existing algorithms, TSK-TL has better performance in EEG recognition of epilepsy.

Epilepsy Signal Recognition Using Online Transfer TSK Fuzzy Classifier Underlying Classification Error and Joint Distribution Consensus Regularization

In this study, an online transfer TSK fuzzy classifier O-T-TSK-FC is proposed for recognizing epilepsy signals. Compared with most of the existing transfer learning models, O-T-TSK-FC enjoys its merits from the following three aspects: 1) Since different patients often response to the same neuronal firing stimulation in different neural manners, the labeled data in the source domain cannot accurately represent the primary EEG data in the target domain. Therefore, we design an objective function which can integrate with subject-specific data in the target domain to induce the target predictive function. 2) A new regularization used for knowledge transfer is proposed from the perspective of error consensus, and its rationality is explained from the perspective of probability density estimation. 3) Clustering is used to partition source domains so as to reduce the computation of O-T-TSK-FC without affecting its performance. Based on the EEG signals collected from Bonn University, six different online scenarios for transfer learning are constructed. Experimental results on them show that O-T-TSK-FC performs better than benchmarking algorithms and robustly.

Transferred Subspace Learning Based on Non-negative Matrix Factorization for EEG Signal Classification

EEG signal classification has been a research hotspot recently. The combination of EEG signal classification with machine learning technology is very popular. Traditional machine leaning methods for EEG signal classification assume that the EEG signals are drawn from the same distribution. However, the assumption is not always satisfied with the practical applications. In practical applications, the training dataset and the testing dataset are from different but related domains. How to make best use of the training dataset knowledge to improve the testing dataset is critical for these circumstances. In this paper, a novel method combining the non-negative matrix factorization technology and the transfer learning (NMF-TL) is proposed for EEG signal classification. Specifically, the shared subspace is extracted from the testing dataset and training dataset using non-negative matrix factorization firstly and then the shared subspace and the original feature space are combined to obtain the final EEG signal classification results. On the one hand, the non-negative matrix factorization can assure to obtain essential information between the testing and the training dataset; on the other hand, the combination of shared subspace and the original feature space can fully use all the signals including the testing and the training dataset. Extensive experiments on Bonn EEG confirmed the effectiveness of the proposed method.

Classification of EEG signals in epilepsy using a novel integrated TSK fuzzy system

The use of machine learning technology to recognize electrical signals of the brain is becoming increasingly popular. Compared with doctors’ manual judgment, machine learning methods are faster. However, only when its recognition accuracy reaches a high level can it be used in practice. Due to the difference in the data distributions of the training dataset and the test dataset and the lack of training samples, the classification accuracies of general machine learning algorithms are not satisfactory. In fact, among the many machine learning methods used to process epilepsy electroencephalogram (EEG) signals, most are black box methods; however, in medicine, methods with explanatory power are needed. In response to these three challenges, this paper proposes a novel technique based on domain adaptation learning, semi-supervised learning and a fuzzy system. In detail, we use domain adaptation learning to reduce deviation from the data distribution, semi-supervised learning to compensate for the lack of training samples, and the Takagi-Sugen-Kang (TSK) fuzzy system model to improve interpretability. Our experimental results show that the performance of the new method is better than those of most advanced epilepsy classification methods.

Research on athlete skipping surface electromyography and energy consumption based on principal component analysis of wavelet packet

EMG signal acquisition is mostly used in medical research. However, it has not been applied in athletes’ sports state recognition and body state detection, and there are few related studies at present. In order to promote the application of EMG signal acquisition in sports, this study combined with the actual needs of athletes to construct an EMG signal acquisition system that can collect athletes’ motion status. At the same time, in order to improve the effect of EMG signal acquisition, a wavelet packet principal component analysis model is proposed. In addition, in order to ensure the recognition efficiency of athletes’ motion state, this paper uses linear discriminant analysis method as the motion recognition assistant algorithm. Finally, this paper judges the performance of this research model by setting up comparative experiments. The research shows that the wavelet packet principal component analysis model performance is significantly better than the traditional algorithm, and the recognition rate for some subtle motions is also high. In addition, this study provides a theoretical reference for the application of EMG signals in the sports industry.

Cross-Domain Classification Model With Knowledge Utilization Maximization for Recognition of Epileptic EEG Signals

Conventional classification models for epileptic EEG signal recognition need sufficient labeled samples as training dataset. In addition, when training and testing EEG signal samples are collected from different distributions, for example, due to differences in patient groups or acquisition devices, such methods generally cannot perform well. In this paper, a cross-domain classification model with knowledge utilization maximization called CDC-KUM is presented, which takes advantage of the data global structure provided by the labeled samples in the related domain and unlabeled samples in the current domain. Through mapping the data into kernel space, the pairwise constraint regularization term is combined together the predictive differences of the labeled data in the source domain. Meanwhile, the soft clustering regularization term using quadratic weights and Gini-Simpson diversity is applied to exploit the distribution information of unlabeled data in the target domain. Experimental results show that CDC-KUM model outperformed several traditional non-transfer and transfer classification methods for recognition of epileptic EEG signals.

Seizure Classification From EEG Signals Using an Online Selective Transfer TSK Fuzzy Classifier With Joint Distribution Adaption and Manifold Regularization

To recognize abnormal electroencephalogram (EEG) signals for epileptics, in this study, we proposed an online selective transfer TSK fuzzy classifier underlying joint distribution adaption and manifold regularization. Compared with most of the existing transfer classifiers, our classifier has its own characteristics: (1) the labeled EEG epochs from the source domain cannot accurately represent the primary EEG epochs in the target domain. Our classifier can make use of very few calibration data in the target domain to induce the target predictive function. (2) A joint distribution adaption is used to minimize the marginal distribution distance and the conditional distribution distance between the source domain and the target domain. (3) Clustering techniques are used to select source domains so that the computational complexity of our classifier is reduced. We construct six transfer scenarios based on the original EEG signals provided by the Bonn University to verify the performance of our classifier and introduce four baselines and a transfer support vector machine (SVM) for benchmarking studies. Experimental results indicate that our classifier wins the best performance and is not very sensitive to its parameters.

Epileptic States Recognition Using Transfer Learning

Automatic recognition of electroencephalogram (EEG) signals plays a major role in epilepsy diagnosis and assessment. However, the recognition accuracy of conventional methods is usually not satisfactory because of the inconsistent distribution of training and testing data in practical applications. To overcome this problem, we used cross-domain mean joint approximation embedding (CMJAE) transductive transfer learning method to realize the knowledge transfer from the training data to the testing data by measuring the distribution difference between them. We combined the subspace learning and joint distribution to adapt the marginal and conditional distribution discrepancy. Our method was able to effectively learn a model for the testing data from training data with different distribution at a low computational complexity cost. On a public dataset, an ad-hoc cross-validation scheme of the proposed method exhibited that the average recognition accuracy, sensitivity, specificity of different states was 97.5%, 94.3%, 92.7% respectively, much better than conventional machine learning or deep learning methods, which may serve as a promising strategy for epileptic states recognition algorithms.

Compositional model based on factorial evolution for realizing multi-task learning in bacterial virulent protein prediction

The ability of multitask learning promulgated its sovereignty in the machine learning field with the diversified application including but not limited to bioinformatics and pattern recognition. Bioinformatics provides a wide range of applications for Multitask Learning (MTL) methods. Identification of Bacterial virulent protein is one such application that helps in understanding the virulence mechanism for the design of drug and vaccine. However, the limiting factor in a reliable prediction model is the scarcity of the experimentally verified training data. To deal with, casting the problem in a Multitask Learning scenario, could be beneficial. Reusability of auxiliary data from related multiple domains in the prediction of target domain with limited labeled data is the primary objective of multitask learning model. Due to the amalgamation of multiple related data, it is possible that the probability distribution between the features tends to vary. Therefore, to deal with change amongst the feature distribution, this paper proposes a composite model for multitask learning framework which is based on two principles: discovering the shared parameters for identifying the relationships between tasks and common underlying representation of features amongst the related tasks. Through multi-kernel and factorial evolution, the proposed framework able to discover the shared kernel parameters and latent feature representation that is common amongst the tasks. To examine the benefits of the proposed model, an extensive experiment is performed on the freely available dataset at VirulentPred web server. Based on the results, we found that multitask learning model performs better than the conventional single task model. Additionally, our findings state that if the distribution between the tasks is high, then training the multiple models yield slightly better prediction. However, if the data distribution difference is low, multitask learning significantly outperforms the individual learning.

Generalized Hidden-Mapping Transductive Transfer Learning for Recognition of Epileptic Electroencephalogram Signals

Electroencephalogram (EEG) signal identification based on intelligent models is an important means in epilepsy detection. In the recognition of epileptic EEG signals, traditional intelligent methods usually assume that the training dataset and testing dataset have the same distribution, and the data available for training are adequate. However, these two conditions cannot always be met in practice, which reduces the ability of the intelligent recognition model obtained in detecting epileptic EEG signals. To overcome this issue, an effective strategy is to introduce transfer learning in the construction of the intelligent models, where knowledge is learned from the related scenes (source domains) to enhance the performance of model trained in the current scene (target domain). Although transfer learning has been used in EEG signal identification, many existing transfer learning techniques are designed only for a specific intelligent model, which limit their applicability to other classical intelligent models. To extend the scope of application, the generalized hidden-mapping transductive learning method is proposed to realize transfer learning for several classical intelligent models, including feedforward neural networks, fuzzy systems, and kernelized linear models. These intelligent models can be trained effectively by the proposed method even though the data available are insufficient for model training, and the generalization abilities of the trained model is also enhanced by transductive learning. A number of experiments are carried out to demonstrate the effectiveness of the proposed method in epileptic EEG recognition. The results show that the method is highly competitive or superior to some existing state-of-the-art methods.

Recognition of Multiclass Epileptic EEG Signals Based on Knowledge and Label Space Inductive Transfer

Electroencephalogram (EEG) signal recognition based on machine learning models is becoming more and more attractive in epilepsy detection. For multiclass epileptic EEG signal recognition tasks including the detection of epileptic EEG signals from different blends of different background data and epilepsy EEG data and the classification of different types of seizures, we may perhaps encounter two serious challenges: (1) a large amount of EEG signal data for training are not available and (2) the models for epileptic EEG signal recognition are often so complicated that they are not as easy to explain as a linear model. In this paper, we utilize the proposed transfer learning technique to circumvent the first challenge and then design a novel linear model to circumvent the second challenge. Concretely, we originally combine γ -LSR with transfer learning to propose a novel knowledge and label space inductive transfer learning model for multiclass EEG signal recognition. By transferring both knowledge and the proposed generalized label space from the source domain to the target domain, the proposed model achieves enhanced classification performance on the target domain without the use of kernel trick. In contrast to the other inductive transfer learning methods, the method uses the generalized linear model such that it becomes simpler and more interpretable. Experimental results indicate the effectiveness of the proposed method for multiclass epileptic EEG signal recognition.

Glioma Grading on Conventional MR Images: A Deep Learning Study With Transfer Learning

Background: Accurate glioma grading before surgery is of the utmost importance in treatment planning and prognosis prediction. But previous studies on magnetic resonance imaging (MRI) images were not effective enough. According to the remarkable performance of convolutional neural network (CNN) in medical domain, we hypothesized that a deep learning algorithm can achieve high accuracy in distinguishing the World Health Organization (WHO) low grade and high grade gliomas.

Methods: One hundred and thirteen glioma patients were retrospectively included. Tumor images were segmented with a rectangular region of interest (ROI), which contained about 80% of the tumor. Then, 20% data were randomly selected and leaved out at patient-level as test dataset. AlexNet and GoogLeNet were both trained from scratch and fine-tuned from models that pre-trained on the large scale natural image database, ImageNet, to magnetic resonance images. The classification task was evaluated with five-fold cross-validation (CV) on patient-level split.

Results: The performance measures, including validation accuracy, test accuracy and test area under curve (AUC), averaged from five-fold CV of GoogLeNet which trained from scratch were 0.867, 0.909, and 0.939, respectively. With transfer learning and fine-tuning, better performances were obtained for both AlexNet and GoogLeNet, especially for AlexNet. Meanwhile, GoogLeNet performed better than AlexNet no matter trained from scratch or learned from pre-trained model.

Conclusion: In conclusion, we demonstrated that the application of CNN, especially trained with transfer learning and fine-tuning, to preoperative glioma grading improves the performance, compared with either the performance of traditional machine learning method based on hand-crafted features, or even the CNNs trained from scratch.

Seizure Classification From EEG Signals Using Transfer Learning, Semi-Supervised Learning and TSK Fuzzy System

Recognition of epileptic seizures from offline EEG signals is very important in clinical diagnosis of epilepsy. Compared with manual labeling of EEG signals by doctors, machine learning approaches can be faster and more consistent. However, the classification accuracy is usually not satisfactory for two main reasons: the distributions of the data used for training and testing may be different, and the amount of training data may not be enough. In addition, most machine learning approaches generate black-box models that are difficult to interpret. In this paper, we integrate transductive transfer learning, semi-supervised learning and TSK fuzzy system to tackle these three problems. More specifically, we use transfer learning to reduce the discrepancy in data distribution between the training and testing data, employ semi-supervised learning to use the unlabeled testing data to remedy the shortage of training data, and adopt TSK fuzzy system to increase model interpretability. Two learning algorithms are proposed to train the system. Our experimental results show that the proposed approaches can achieve better performance than many state-of-the-art seizure classification algorithms.

Enhanced Knowledge-Leverage-Based TSK Fuzzy System Modeling for Inductive Transfer Learning

The knowledge-leverage-based Takagi--Sugeno--Kang fuzzy system (KL-TSK-FS) modeling method has shown promising performance for fuzzy modeling tasks where transfer learning is required. However, the knowledge-leverage mechanism of the KL-TSK-FS can be further improved. This is because available training data in the target domain are not utilized for the learning of antecedents and the knowledge transfer mechanism from a source domain to the target domain is still too simple for the learning of consequents when a Takagi--Sugeno--Kang fuzzy system (TSK-FS) model is trained in the target domain. The proposed method, that is, the enhanced KL-TSK-FS (EKL-TSK-FS), has two knowledge-leverage strategies for enhancing the parameter learning of the TSK-FS model for the target domain using available information from the source domain. One strategy is used for the learning of antecedent parameters, while the other is for consequent parameters. It is demonstrated that the proposed EKL-TSK-FS has higher transfer learning abilities than the KL-TSK-FS. In addition, the EKL-TSK-FS has been further extended for the scene of the multisource domain.