EEG classification using sparse Bayesian extreme learning machine for brain–computer interface

STaRNet: A spatio-temporal and Riemannian network for high-performance motor imagery decoding

Brain-computer interfaces (BCIs), representing a transformative form of human-computer interaction, empower users to interact directly with external environments through brain signals. In response to the demands for high accuracy, robustness, and end-to-end capabilities within BCIs based on motor imagery (MI), this paper introduces STaRNet, a novel model that integrates multi-scale spatio-temporal convolutional neural networks (CNNs) with Riemannian geometry. Initially, STaRNet integrates a multi-scale spatio-temporal feature extraction module that captures both global and local features, facilitating the construction of Riemannian manifolds from these comprehensive spatio-temporal features. Subsequently, a matrix logarithm operation transforms the manifold-based features into the tangent space, followed by a dense layer for classification. Without preprocessing, STaRNet surpasses state-of-the-art (SOTA) models by achieving an average decoding accuracy of 83.29% and a kappa value of 0.777 on the BCI Competition IV 2a dataset, and 95.45% accuracy with a kappa value of 0.939 on the High Gamma Dataset. Additionally, a comparative analysis between STaRNet and several SOTA models, focusing on the most challenging subjects from both datasets, highlights exceptional robustness of STaRNet. Finally, the visualizations of learned frequency bands demonstrate that temporal convolutions have learned MI-related frequency bands, and the t-SNE analyses of features across multiple layers of STaRNet exhibit strong feature extraction capabilities. We believe that the accurate, robust, and end-to-end capabilities of the STaRNet will facilitate the advancement of BCIs.

Adaptive Multimodel Knowledge Transfer Matrix Machine for EEG Classification

The emerging matrix learning methods have achieved promising performances in electroencephalogram (EEG) classification by exploiting the structural information between the columns or rows of feature matrices. Due to the intersubject variability of EEG data, these methods generally need to collect a large amount of labeled individual EEG data, which would cause fatigue and inconvenience to the subjects. Insufficient subject-specific EEG data will weaken the generalization capability of the matrix learning methods in neural pattern decoding. To overcome this dilemma, we propose an adaptive multimodel knowledge transfer matrix machine (AMK-TMM), which can selectively leverage model knowledge from multiple source subjects and capture the structural information of the corresponding EEG feature matrices. Specifically, by incorporating least-squares (LS) loss with spectral elastic net regularization, we first present an LS support matrix machine (LS-SMM) to model the EEG feature matrices. To boost the generalization capability of LS-SMM in scenarios with limited EEG data, we then propose a multimodel adaption method, which can adaptively choose multiple correlated source model knowledge with a leave-one-out cross-validation strategy on the available target training data. We extensively evaluate our method on three independent EEG datasets. Experimental results demonstrate that our method achieves promising performances on EEG classification.

EBi-LSTM: an enhanced bi-directional LSTM for time-series data classification by heuristic development of optimal feature integration in brain computer interface

Generally, time series data is referred to as the sequential representation of data that observes from different applications. Therefore, such expertise can use Electroencephalography (EEG) signals to fetch data regarding brain neural activities in brain-computer interface (BCI) systems. Due to massive and myriads data, the signals are appealed in a non-stationary format that ends with a poor quality resolution. To overcome this existing issue, a new framework of enhanced deep learning methods is proposed. The source signals are collected and undergo feature extraction in four ways. Hence, the features are concatenated to enhance the performance. Subsequently, the concatenated features are given to probability ratio-based Reptile Search Algorithm (PR-RSA) to select the optimal features. Finally, the classification is conducted using Enhanced Bi-directional Long Short-Term Memory (EBi-LSTM), where the hyperparameters are optimized by PR-RSA. Throughout the result analysis, it is confirmed that the offered model obtains elevated classification accuracy, and thus tends to increase the performance.

TSPNet: a time-spatial parallel network for classification of EEG-based multiclass upper limb motor imagery BCI

The classification of electroencephalogram (EEG) motor imagery signals has emerged as a prominent research focus within the realm of brain-computer interfaces. Nevertheless, the conventional, limited categories (typically just two or four) offered by brain-computer interfaces fail to provide an extensive array of control modes. To address this challenge, we propose the Time-Spatial Parallel Network (TSPNet) for recognizing six distinct categories of upper limb motor imagery. Within TSPNet, temporal and spatial features are extracted separately, with the time dimension feature extractor and spatial dimension feature extractor performing their respective functions. Following this, the Time-Spatial Parallel Feature Extractor is employed to decouple the connection between temporal and spatial features, thus diminishing feature redundancy. The Time-Spatial Parallel Feature Extractor deploys a gating mechanism to optimize weight distribution and parallelize time-spatial features. Additionally, we introduce a feature visualization algorithm based on signal occlusion frequency to facilitate a qualitative analysis of TSPNet. In a six-category scenario, TSPNet achieved an accuracy of 49.1% ± 0.043 on our dataset and 49.7% ± 0.029 on a public dataset. Experimental results conclusively establish that TSPNet outperforms other deep learning methods in classifying data from these two datasets. Moreover, visualization results vividly illustrate that our proposed framework can generate distinctive classifier patterns for multiple categories of upper limb motor imagery, discerned through signals of varying frequencies. These findings underscore that, in comparison to other deep learning methods, TSPNet excels in intention recognition, which bears immense significance for non-invasive brain-computer interfaces.

Multi-domain feature joint optimization based on multi-view learning for improving the EEG decoding

Background

Brain-computer interface (BCI) systems based on motor imagery (MI) have been widely used in neurorehabilitation. Feature extraction applied by the common spatial pattern (CSP) is very popular in MI classification. The effectiveness of CSP is highly affected by the frequency band and time window of electroencephalogram (EEG) segments and channels selected.

Objective

In this study, the multi-domain feature joint optimization (MDFJO) based on the multi-view learning method is proposed, which aims to select the discriminative features enhancing the classification performance.

Method

The channel patterns are divided using the Fisher discriminant criterion (FDC). Furthermore, the raw EEG is intercepted for multiple sub-bands and time interval signals. The high-dimensional features are constructed by extracting features from CSP on each EEG segment. Specifically, the multi-view learning method is used to select the optimal features, and the proposed feature sparsification strategy on the time level is proposed to further refine the optimal features.

Results

Two public EEG datasets are employed to validate the proposed MDFJO method. The average classification accuracy of the MDFJO in Data 1 and Data 2 is 88.29 and 87.21%, respectively. The classification result of MDFJO was significantly better than MSO (p < 0.05), FBCSP32 (p < 0.01), and other competing methods (p < 0.001).

Conclusion

Compared with the CSP, sparse filter band common spatial pattern (SFBCSP), and filter bank common spatial pattern (FBCSP) methods with channel numbers 16, 32 and all channels as well as MSO, the MDFJO significantly improves the test accuracy. The feature sparsification strategy proposed in this article can effectively enhance classification accuracy. The proposed method could improve the practicability and effectiveness of the BCI system.

Improving EEG Decoding via Clustering-Based Multitask Feature Learning

Accurate electroencephalogram (EEG) pattern decoding for specific mental tasks is one of the key steps for the development of brain-computer interface (BCI), which is quite challenging due to the considerably low signal-to-noise ratio of EEG collected at the brain scalp. Machine learning provides a promising technique to optimize EEG patterns toward better decoding accuracy. However, existing algorithms do not effectively explore the underlying data structure capturing the true EEG sample distribution and, hence, can only yield a suboptimal decoding accuracy. To uncover the intrinsic distribution structure of EEG data, we propose a clustering-based multitask feature learning algorithm for improved EEG pattern decoding. Specifically, we perform affinity propagation-based clustering to explore the subclasses (i.e., clusters) in each of the original classes and then assign each subclass a unique label based on a one-versus-all encoding strategy. With the encoded label matrix, we devise a novel multitask learning algorithm by exploiting the subclass relationship to jointly optimize the EEG pattern features from the uncovered subclasses. We then train a linear support vector machine with the optimized features for EEG pattern decoding. Extensive experimental studies are conducted on three EEG data sets to validate the effectiveness of our algorithm in comparison with other state-of-the-art approaches. The improved experimental results demonstrate the outstanding superiority of our algorithm, suggesting its prominent performance for EEG pattern decoding in BCI applications.

Extreme Learning Machine Design for Dealing with Unrepresentative Features

Extreme Learning Machines (ELMs) have become a popular tool for the classification of electroencephalography (EEG) signals for Brain Computer Interfaces. This is so mainly due to their very high training speed and generalization capabilities. Another important advantage is that they have only one hyperparameter that must be calibrated: the number of hidden nodes. While most traditional approaches dictate that this parameter should be chosen smaller than the number of available training examples, in this article we argue that, in the case of problems in which the data contain unrepresentative features, such as in EEG classification problems, it is beneficial to choose a much larger number of hidden nodes. We characterize this phenomenon, explain why this happens and exhibit several concrete examples to illustrate how ELMs behave. Furthermore, as searching for the optimal number of hidden nodes could be time consuming in enlarged ELMs, we propose a new training scheme, including a novel pruning method. This scheme provides an efficient way of finding the optimal number of nodes, making ELMs more suitable for dealing with real time EEG classification problems. Experimental results using synthetic data and real EEG data show a major improvement in the training time with respect to most traditional and state of the art ELM approaches, without jeopardising classification performance and resulting in more compact networks.

A Hybrid Approach for MS Diagnosis Through Nonlinear EEG Descriptors and Metaheuristic Optimized Classification Learning

Multiple sclerosis (MS), a disease of the central nervous system, affects the white matter of the brain. Neurologists interpret magnetic resonance images that are often complicated, time-consuming, and contradictory. Using EEG signals, this disease can be analyzed and diagnosed more accurately. However, it is imperative that MS be diagnosed by specialists using assistive technology. Until now, a few methods have been proposed in this field that are sometimes associated with different challenges in analysis. This paper presents a hybrid approach to MS diagnosis in order to decrease classification error rates. Using the proposed method, EEG descriptors in both the time and frequency domains are analyzed. After the feature extraction stage, a modified version of the ant colony optimization method (m-ACO) was used to select the appropriate subset of features. Then, the support vector machine is used to determine whether the disease exists. A metaheuristic algorithm adjusts the support vector machine's parameters to withstand overfitting challenges. Despite a limited number of input channels, significant classification accuracy has been achieved using wavelet analysis techniques, dividing all five subbands of EEG signals, signal windowing, and extracting efficient features from the data. Additionally, alpha, beta, and gamma bands of the signal are important, and the accuracy, sensitivity, and specificity levels are higher than 98.5%. Compared to similar MS diagnostic methods, the proposed method achieved significantly higher diagnostic accuracy. Application and implementation of this method can be effective in treating neurological diseases, including multiple sclerosis.

Automatic Muscle Artifacts Identification and Removal from Single-Channel EEG Using Wavelet Transform with Meta-Heuristically Optimized Non-Local Means Filter

Electroencephalogram (EEG) signals may get easily contaminated by muscle artifacts, which may lead to wrong interpretation in the brain–computer interface (BCI) system as well as in various medical diagnoses. The main objective of this paper is to remove muscle artifacts without distorting the information contained in the EEG. A novel multi-stage EEG denoising method is proposed for the first time in which wavelet packet decomposition (WPD) is combined with a modified non-local means (NLM) algorithm. At first, the artifact EEG signal is identified through a pre-trained classifier. Next, the identified EEG signal is decomposed into wavelet coefficients and corrected through a modified NLM filter. Finally, the artifact-free EEG is reconstructed from corrected wavelet coefficients through inverse WPD. To optimize the filter parameters, two meta-heuristic algorithms are used in this paper for the first time. The proposed system is first validated on simulated EEG data and then tested on real EEG data. The proposed approach achieved average mutual information (MI) as 2.9684 ± 0.7045 on real EEG data. The result reveals that the proposed system outperforms recently developed denoising techniques with higher average MI, which indicates that the proposed approach is better in terms of quality of reconstruction and is fully automatic.

Hand Motor Imagery Classification Using Effective Connectivity and Hierarchical Machine Learning in EEG Signals

Background

Motor Imagery (MI) Brain Computer Interface (BCI) directly links central nervous system to a computer or a device. Most MI-BCI structures rely on features of a single channel of Electroencephalogram (EEG). However, to provide more valuable features, the relationships among EEG channels in the form of effective brain connectivity analysis must be considered.

Objective

This study aims to identify a set of robust and discriminative effective connectivity features from EEG signals and to develop a hierarchical machine learning structure for discrimination of left and right hand MI task effectively.

Material and Methods

In this analytical study, we estimated effective connectivity using Granger Causality (GC) methods namely, Generalized Partial Directed Coherence (GPDC), Directed Transfer Function (DTF) and direct Directed Transfer Function (dDTF). These measures determine the transient causal relation between different brain areas. Then a feature subset selection method based on Kruskal-Wallis test was performed to choose most significant directed causal connection between channels. Moreover, the minimal-redundancy-maximal-relevance feature selection method is applied to discard non-significance features. Finally, support vector machine method is used for classification.

Results

The maximum value of the classification accuracies using GC methods over different frequency bands in 29 subjects in 60 trial is approximately 84% in Mu (8-12 Hz) - Beta1 (12 - 15 Hz) frequency band using GPDC method.

Conclusion

This new hierarchical automated BCI system could be applied for discrimination of left and right hand MI tasks from EEG signal, effectively.

Recent Advances and Current Trends in Brain-Computer Interface (BCI) Research and Their Applications

Brain-Computer Interface (BCI) provides direct communication between the brain and an external device. BCI systems have become a trendy field of research in recent years. These systems can be used in a variety of applications to help both disabled and healthy people. Concerning significant BCI progress, we may assume that these systems are not very far from real-world applications. This review has taken into account current trends in BCI research. In this survey, one hundred most cited articles from the WOS database were selected over the last four years. This survey is divided into several sectors. These sectors are Medicine, Communication and Control, Entertainment, and Other BCI applications. The application area, recording method, signal acquisition types, and countries of origin have been identified in each article. This survey provides an overview of the BCI articles published from 2016 to 2020 and their current trends and advances in different application areas.

A Review of the Role of Machine Learning Techniques towards Brain–Computer Interface Applications

This review article provides a deep insight into the Brain–Computer Interface (BCI) and the application of Machine Learning (ML) technology in BCIs. It investigates the various types of research undertaken in this realm and discusses the role played by ML in performing different BCI tasks. It also reviews the ML methods used for mental state detection, mental task categorization, emotion classification, electroencephalogram (EEG) signal classification, event-related potential (ERP) signal classification, motor imagery categorization, and limb movement classification. This work explores the various methods employed in BCI mechanisms for feature extraction, selection, and classification and provides a comparative study of reviewed methods. This paper assists the readers to gain information regarding the developments made in BCI and ML domains and future improvements needed for improving and designing better BCI applications.

Brain-Computer Interface: Advancement and Challenges

Brain-Computer Interface (BCI) is an advanced and multidisciplinary active research domain based on neuroscience, signal processing, biomedical sensors, hardware, etc. Since the last decades, several groundbreaking research has been conducted in this domain. Still, no comprehensive review that covers the BCI domain completely has been conducted yet. Hence, a comprehensive overview of the BCI domain is presented in this study. This study covers several applications of BCI and upholds the significance of this domain. Then, each element of BCI systems, including techniques, datasets, feature extraction methods, evaluation measurement matrices, existing BCI algorithms, and classifiers, are explained concisely. In addition, a brief overview of the technologies or hardware, mostly sensors used in BCI, is appended. Finally, the paper investigates several unsolved challenges of the BCI and explains them with possible solutions.

Transfer Extreme Learning Machine with Output Weight Alignment

Extreme Learning Machine (ELM) as a fast and efficient neural network model in pattern recognition and machine learning will decline when the labeled training sample is insufficient. Transfer learning helps the target task to learn a reliable model by using plentiful labeled samples from the different but relevant domain. In this paper, we propose a supervised Extreme Learning Machine with knowledge transferability, called Transfer Extreme Learning Machine with Output Weight Alignment (TELM-OWA). Firstly, it reduces the distribution difference between domains by aligning the output weight matrix of the ELM trained by the labeled samples from the source and target domains. Secondly, the approximation between the interdomain ELM output weight matrix is added to the objective function to further realize the cross-domain transfer of knowledge. Thirdly, we consider the objective function as the least square problem and transform it into a standard ELM model to be efficiently solved. Finally, the effectiveness of the proposed algorithm is verified by classification experiments on 16 sets of image datasets and 6 sets of text datasets, and the result demonstrates the competitive performance of our method with respect to other ELM models and transfer learning approach.

An empirical survey of electroencephalography-based brain-computer interfaces

Objectives

The Electroencephalogram (EEG) signal is modified using the Motor Imagery (MI) and it is utilized for patients with high motor impairments. Hence, the direct relationship between the computer and brain is termed as an EEG-based brain-computer interface (BCI). The objective of this survey is to presents an analysis of the existing distinct BCIs based on EEG.

Methods

This survey provides a detailed review of more than 60 research papers presenting the BCI-based EEG, like motor imagery-based techniques, spatial filtering-based techniques, Steady-State Visual Evoked Potential (SSVEP)-based techniques, machine learning-based techniques, Event-Related Potential (ERP)-based techniques, and online EEG-based techniques. Subsequently, the research gaps and issues of several EEG-based BCI systems are adopted to help the researchers for better future scope.

Results

An elaborative analyses as well as discussion have been provided by concerning the parameters, like evaluation metrics, year of publication, accuracy, implementation tool, and utilized datasets obtained by various techniques.

Conclusions

This survey paper exposes research topics on BCI-based EEG, which helps the researchers and scholars, who are interested in this domain.

Deep Learning Based Inter-subject Continuous Decoding of Motor Imagery for Practical Brain-Computer Interfaces

Inter-subject transfer learning is a long-standing problem in brain-computer interfaces (BCIs) and has not yet been fully realized due to high inter-subject variability in the brain signals related to motor imagery (MI). The recent success of deep learning-based algorithms in classifying different brain signals warrants further exploration to determine whether it is feasible for the inter-subject continuous decoding of MI signals to provide contingent neurofeedback which is important for neurorehabilitative BCI designs. In this paper, we have shown how a convolutional neural network (CNN) based deep learning framework can be used for inter-subject continuous decoding of MI related electroencephalographic (EEG) signals using the novel concept of Mega Blocks for adapting the network against inter-subject variabilities. These Mega Blocks have the capacity to repeat a specific architectural block several times such as one or more convolutional layers in a single Mega Block. The parameters of such Mega Blocks can be optimized using Bayesian hyperparameter optimization. The results, obtained on the publicly available BCI competition IV-2b dataset, yields an average inter-subject continuous decoding accuracy of 71.49% (κ = 0.42) and 70.84% (κ = 0.42) for two different training methods such as adaptive moment estimation (Adam) and stochastic gradient descent (SGDM), respectively, in 7 out of 9 subjects. Our results show for the first time that it is feasible to use CNN based architectures for inter-subject continuous decoding with a sufficient level of accuracy for developing calibration-free MI-BCIs for practical purposes.

Spatial-Frequency Feature Learning and Classification of Motor Imagery EEG Based on Deep Convolution Neural Network

EEG pattern recognition is an important part of motor imagery- (MI-) based brain computer interface (BCI) system. Traditional EEG pattern recognition algorithm usually includes two steps, namely, feature extraction and feature classification. In feature extraction, common spatial pattern (CSP) is one of the most frequently used algorithms. However, in order to extract the optimal CSP features, prior knowledge and complex parameter adjustment are often required. Convolutional neural network (CNN) is one of the most popular deep learning models at present. Within CNN, feature learning and pattern classification are carried out simultaneously during the procedure of iterative updating of network parameters; thus, it can remove the complicated manual feature engineering. In this paper, we propose a novel deep learning methodology which can be used for spatial-frequency feature learning and classification of motor imagery EEG. Specifically, a multilayer CNN model is designed according to the spatial-frequency characteristics of MI EEG signals. An experimental study is carried out on two MI EEG datasets (BCI competition III dataset IVa and a self-collected right index finger MI dataset) to validate the effectiveness of our algorithm in comparison with several closely related competing methods. Superior classification performance indicates that our proposed method is a promising pattern recognition algorithm for MI-based BCI system.

Analyzing the Effectiveness of the Brain-Computer Interface for Task Discerning Based on Machine Learning

The aim of the study is to compare electroencephalographic (EEG) signal feature extraction methods in the context of the effectiveness of the classification of brain activities. For classification, electroencephalographic signals were obtained using an EEG device from 17 subjects in three mental states (relaxation, excitation, and solving logical task). Blind source separation employing independent component analysis (ICA) was performed on obtained signals. Welch's method, autoregressive modeling, and discrete wavelet transform were used for feature extraction. Principal component analysis (PCA) was performed in order to reduce the dimensionality of feature vectors. k-Nearest Neighbors (kNN), Support Vector Machines (SVM), and Neural Networks (NN) were employed for classification. Precision, recall, F1 score, as well as a discussion based on statistical analysis, were shown. The paper also contains code utilized in preprocessing and the main part of experiments.

Analysis of Recurrent Neural Network and Predictions

This paper analyzes the operation principle and predicted value of the recurrent-neural-network (RNN) structure, which is the most basic and suitable for the change of time in the structure of a neural network for various types of artificial intelligence (AI). In particular, an RNN in which all connections are symmetric guarantees that it will converge. The operating principle of a RNN is based on linear data combinations and is composed through the synthesis of nonlinear activation functions. Linear combined data are similar to the autoregressive-moving average (ARMA) method of statistical processing. However, distortion due to the nonlinear activation function in RNNs causes the predicted value to be different from the predicted ARMA value. Through this, we know the limit of the predicted value of an RNN and the range of prediction that changes according to the learning data. In addition to mathematical proofs, numerical experiments confirmed our claims.

Bacomics: a comprehensive cross area originating in the studies of various brain-apparatus conversations

The brain is the most important organ of the human body, and the conversations between the brain and an apparatus can not only reveal a normally functioning or a dysfunctional brain but also can modulate the brain. Here, the apparatus may be a nonbiological instrument, such as a computer, and the consequent brain-computer interface is now a very popular research area with various applications. The apparatus may also be a biological organ or system, such as the gut and muscle, and their efficient conversations with the brain are vital for a healthy life. Are there any common bases that bind these different scenarios? Here, we propose a new comprehensive cross area: Bacomics, which comes from brain-apparatus conversations (BAC) + omics. We take Bacomics to cover at least three situations: (1) The brain is normal, but the conversation channel is disabled, as in amyotrophic lateral sclerosis. The task is to reconstruct or open up new channels to reactivate the brain function. (2) The brain is in disorder, such as in Parkinson's disease, and the work is to utilize existing or open up new channels to intervene, repair and modulate the brain by medications or stimulation. (3) Both the brain and channels are in order, and the goal is to enhance coordinated development between the brain and apparatus. In this paper, we elaborate the connotation of BAC into three aspects according to the information flow: the issue of output to the outside (BAC-1), the issue of input to the brain (BAC-2) and the issue of unity of brain and apparatus (BAC-3). More importantly, there are no less than five principles that may be taken as the cornerstones of Bacomics, such as feedforward and feedback control, brain plasticity, harmony, the unity of opposites and systems principles. Clearly, Bacomics integrates these seemingly disparate domains, but more importantly, opens a much wider door for the research and development of the brain, and the principles further provide the general framework in which to realize or optimize these various conversations.

Monitoring Depth of Anesthesia Based on Hybrid Features and Recurrent Neural Network

Electroencephalogram (EEG) signals contain valuable information about the different physiological states of the brain, with a variety of linear and nonlinear features that can be used to investigate brain activity. Monitoring the depth of anesthesia (DoA) with EEG is an ongoing challenge in anesthesia research. In this paper, we propose a novel method based on Long Short-Term Memory (LSTM) and a sparse denoising autoencoder (SDAE) to combine the hybrid features of EEG to monitor the DoA. The EEG signals were preprocessed using filtering, etc., and then more than ten features including sample entropy, permutation entropy, spectra, and alpha-ratio were extracted from the EEG signal. We then integrated the optional features such as permutation entropy and alpha-ratio to extract the essential structure and learn the most efficient temporal model for monitoring the DoA. Compared with using a single feature, the proposed model could accurately estimate the depth of anesthesia with higher prediction probability (P_k). Experimental results evaluated on the datasets demonstrated that our proposed method provided better performance than the methods using permutation entropy, alpha-ratio, LSTM, and other traditional indices.

Regularized Group Sparse Discriminant Analysis for P300-Based Brain–Computer Interface

Event-related potentials (ERPs) especially P300 are popular effective features for brain–computer interface (BCI) systems based on electroencephalography (EEG). Traditional ERP-based BCI systems may perform poorly for small training samples, i.e. the undersampling problem. In this study, the ERP classification problem was investigated, in particular, the ERP classification in the high-dimensional setting with the number of features larger than the number of samples was studied. A flexible group sparse discriminative analysis algorithm based on Moreau–Yosida regularization was proposed for alleviating the undersampling problem. An optimization problem with the group sparse criterion was presented, and the optimal solution was proposed by using the regularized optimal scoring method. During the alternating iteration procedure, the feature selection and classification were performed simultaneously. Two P300-based BCI datasets were used to evaluate our proposed new method and compare it with existing standard methods. The experimental results indicated that the features extracted via our proposed method are efficient and provide an overall better P300 classification accuracy compared with several state-of-the-art methods.

An Enhanced Algorithm of RNN Using Trend in Time-Series

The concept of trend in data and a novel neural network method for the forecasting ofupcoming time-series data are proposed in this paper. The proposed method extracts two datasets—the trend and the remainder—resulting in two separate learning sets for training. This methodworks sufficiently, even when only using a simple recurrent neural network (RNN). The proposedscheme is demonstrated to achieve better performance in selected real-life examples, compared toother averaging-based statistical forecast methods and other recurrent methods, such as longshort-term memory (LSTM).

Implementation strategy of a CNN model affects the performance of CT assessment of EGFR mutation status in lung cancer patients

OBJECTIVE

To compare CNN models implemented using different strategies in the CT assessment of EGFR mutation status in patients with lung adenocarcinoma.

METHODS

1,010 consecutive lung adenocarcinoma patients with known EGFR mutation status were randomly divided into a training set (n=810) and a testing set (n=200). CNN models were constructed based on ResNet-101 architecture but implemented using different strategies: dimension filters (2D/3D), input sizes (small/middle/large and their fusion), slicing methods (transverse plane only and arbitrary multi-view planes), and training approaches (from scratch and fine-tuning a pre-trained CNN). The performance of the CNN models was compared using AUC.

RESULTS

The fusion approach yielded consistently better performance than other input sizes, although the effect often did not reach statistical significance. Multi-view slicing was significantly superior to the transverse method when fine-tuning a pre-trained 2D CNN but not a CNN trained from scratch. The 3D CNN was significantly better than the 2D transverse plane method but only marginally better than the multi-view slicing method when trained from scratch. The highest performance (AUC=0.838) was achieved for the fine-tuned 2D CNN model when built using the fusion input size and multi-view slicing method.

CONCLUSION

The assessment of EGFR mutation status in patients is more accurate when CNN models use more spatial information and are fine-tuned by transfer learning. Our finding about implementation strategy of a CNN model could be a guidance to other medical 3D images applications. Compared with other published studies which used medical images to identify EGFR mutation status, our CNN model achieved the best performance in a biggest patient cohort.

Environment Sound Classification Using a Two-Stream CNN Based on Decision-Level Fusion

With the popularity of using deep learning-based models in various categorization problems and their proven robustness compared to conventional methods, a growing number of researchers have exploited such methods in environment sound classification tasks in recent years. However, the performances of existing models use auditory features like log-mel spectrogram (LM) and mel frequency cepstral coefficient (MFCC), or raw waveform to train deep neural networks for environment sound classification (ESC) are unsatisfactory. In this paper, we first propose two combined features to give a more comprehensive representation of environment sounds Then, a fourfour-layer convolutional neural network (CNN) is presented to improve the performance of ESC with the proposed aggregated features. Finally, the CNN trained with different features are fused using the Dempster-Shafer evidence theory to compose TSCNN-DS model. The experiment results indicate that our combined features with the four-layer CNN are appropriate for environment sound taxonomic problems and dramatically outperform other conventional methods. The proposed TSCNN-DS model achieves a classification accuracy of 97.2%, which is the highest taxonomic accuracy on UrbanSound8K datasets compared to existing models.

Strength and Similarity Guided Group-level Brain Functional Network Construction for MCI Diagnosis

Sparse representation-based brain functional network modeling often results in large inter-subject variability in the network structure. This could reduce the statistical power in group comparison, or even deteriorate the generalization capability of the individualized diagnosis of brain diseases. Although group sparse representation (GSR) can alleviate such a limitation by increasing network similarity across subjects, it could, in turn, fail in providing satisfactory separability between the subjects from different groups (e.g., patients vs. controls). In this study, we propose to integrate individual functional connectivity (FC) information into the GSR-based network construction framework to achieve higher between-group separability while maintaining the merit of within-group consistency. Our method was based on an observation that the subjects from the same group have generally more similar FC patterns than those from different groups. To this end, we propose our new method, namely "strength and similarity guided GSR (SSGSR)", which exploits both BOLD signal temporal correlation-based "low-order" FC (LOFC) and inter-subject LOFC-profile similarity-based "high-order" FC (HOFC) as two priors to jointly guide the GSR-based network modeling. Extensive experimental comparisons are carried out, with the rs-fMRI data from mild cognitive impairment (MCI) subjects and healthy controls, between the proposed algorithm and other state-of-the-art brain network modeling approaches. Individualized MCI identification results show that our method could achieve a balance between the individually consistent brain functional network construction and the adequately maintained inter-group brain functional network distinctions, thus leading to a more accurate classification result. Our method also provides a promising and generalized solution for the future connectome-based individualized diagnosis of brain disease.

Investigating EEG Patterns for Dual-Stimuli Induced Human Fear Emotional State

Most electroencephalography (EEG) based emotion recognition systems make use of videos and images as stimuli. Few used sounds, and even fewer studies were found involving self-induced emotions. Furthermore, most of the studies rely on single stimuli to evoke emotions. The question of "whether different stimuli for same emotion elicitation generate any subject-independent correlations" remains unanswered. This paper introduces a dual modality based emotion elicitation paradigm to investigate if emotions can be classified induced with different stimuli. A method has been proposed based on common spatial pattern (CSP) and linear discriminant analysis (LDA) to analyze human brain signals for fear emotions evoked with two different stimuli. Self-induced emotional imagery is one of the considered stimuli, while audio/video clips are used as the other stimuli. The method extracts features from the CSP algorithm and LDA performs classification. To investigate associated EEG correlations, a spectral analysis was performed. To further improve the performance, CSP was compared with other regularized techniques. Critical EEG channels are identified based on spatial filter weights. To the best of our knowledge, our work provides the first contribution for the assessment of EEG correlations in the case of self versus video induced emotions captured with a commercial grade EEG device.

A Hybrid Proposed Fundus Image Enhancement Framework for Diabetic Retinopathy

Diabetic retinopathy (DR) is a complication of diabetes and is known as visual impairment, and is diagnosed in various ethnicities of the working-age population worldwide. Fundus angiography is a widely applicable modality used by ophthalmologists and computerized applications to detect DR-based clinical features such as microaneurysms (MAs), hemorrhages (HEMs), and exudates (EXs) for early screening of DR. Fundus images are usually acquired using funduscopic cameras in varied light conditions and angles. Therefore, these images are prone to non-uniform illumination, poor contrast, transmission error, low brightness, and noise problems. This paper presents a novel and real-time mechanism of fundus image enhancement used for early grading of diabetic retinopathy, macular degeneration, retinal neoplasms, and choroid disruptions. The proposed system is based on two folds: (i) An RGB fundus image is initially taken and converted into a color appearance module (called lightness and denoted as J) of the CIECAM02 color space model to obtain image information in grayscale with bright light. Afterwards, in step (ii), the achieved J component is processed using a nonlinear contrast enhancement approach to improve the textural and color features of the fundus image without any further extraction steps. To test and evaluate the strength of the proposed technique, several performance and quality parameters—namely peak signal-to-noise ratio (PSNR), contrast-to-noise ratio (CNR), entropy (content information), histograms (intensity variation), and a structure similarity index measure (SSIM)—were applied to 1240 fundus images comprised of two publicly available datasets, DRIVE and MESSIDOR. It was determined from the experiments that the proposed enhancement procedure outperformed histogram-based approaches in terms of contrast, sharpness of fundus features, and brightness. This further revealed that it can be a suitable preprocessing tool for segmentation and classification of DR-related features algorithms.