An enhanced probabilistic LDA for multi-class brain computer interface

Background

There is a growing interest in the study of signal processing and machine learning methods, which may make the brain computer interface (BCI) a new communication channel. A variety of classification methods have been utilized to convert the brain information into control commands. However, most of the methods only produce uncalibrated values and uncertain results.

Methodology/Principal Findings

In this study, we presented a probabilistic method “enhanced BLDA” (EBLDA) for multi-class motor imagery BCI, which utilized Bayesian linear discriminant analysis (BLDA) with probabilistic output to improve the classification performance. EBLDA builds a new classifier that enlarges training dataset by adding test samples with high probability. EBLDA is based on the hypothesis that unlabeled samples with high probability provide valuable information to enhance learning process and generate a classifier with refined decision boundaries. To investigate the performance of EBLDA, we first used carefully designed simulated datasets to study how EBLDA works. Then, we adopted a real BCI dataset for further evaluation. The current study shows that: 1) Probabilistic information can improve the performance of BCI for subjects with high kappa coefficient; 2) With supplementary training samples from the test samples of high probability, EBLDA is significantly better than BLDA in classification, especially for small training datasets, in which EBLDA can obtain a refined decision boundary by a shift of BLDA decision boundary with the support of the information from test samples.

Conclusions/Significance

The proposed EBLDA could potentially reduce training effort. Therefore, it is valuable for us to realize an effective online BCI system, especially for multi-class BCI systems.     

A multi‐metric fish index to assess the environmental condition of estuaries

The development of a multi‐metric fish index, the Estuarine Fish Community Index (EFCI), for assessing estuarine environments is described. The index comprises 14 metrics or measures that represent four broad fish community attributes: species diversity and composition, species abundance, nursery function and trophic integrity. The individual metrics were evaluated using data that were collected on a South African estuary that was degraded and in which rehabilitation measures were implemented. The evaluation suggested that the selected metrics adequately measure the condition of separate but related components of estuarine fish communities and that these reflect environmental condition. Reference conditions and metric thresholds were derived from fish community data collected during an extensive national study. The final multi‐metric index was then constructed and evaluated. The EFCI combines both structural and functional attributes of estuarine fish communities and integrates these to provide both a robust and sensitive method for assessing the ecological condition of estuarine systems. It is also an effective communication tool for converting ecological information into an easily understood format for managers, policy makers and the general public.     

An automatic EEG-based sleep staging system with introducing NAoSP and NAoGP as new metrics for sleep staging systems

Different biological signals are recorded in sleep labs during sleep for the diagnosis and treatment of human sleep problems. Classification of sleep stages with electroencephalography (EEG) is preferred to other biological signals due to its advantages such as providing clinical information, cost-effectiveness, comfort, and ease of use. The evaluation of EEG signals taken during sleep by clinicians is a tiring, time-consuming, and error-prone method. Therefore, it is clinically mandatory to determine sleep stages by using software-supported systems. Like all classification problems, the accuracy rate is used to compare the performance of studies in this domain, but this metric can be accurate when the number of observations is equal in classes. However, since there is not an equal number of observations in sleep stages, this metric is insufficient in the evaluation of such systems. For this purpose, in recent years, Cohen’s kappa coefficient and even the sensitivity of NREM1 have been used for comparing the performance of these systems. Still, none of them examine the system from all dimensions. Therefore, in this study, two new metrics based on the polygon area metric, called the normalized area of sensitivity polygon and normalized area of the general polygon, are proposed for the performance evaluation of sleep staging systems. In addition, a new sleep staging system is introduced using the applications offered by the MATLAB program. The existing systems discussed in the literature were examined with the proposed metrics, and the best systems were compared with the proposed sleep staging system. According to the results, the proposed system excels in comparison with the most advanced machine learning methods. The single-channel method introduced based on the proposed metrics can be used for robust and reliable sleep stage classification from all dimensions required for real-time applications.Electronic supplementary materialThe online version of this article (10.1007/s11571-020-09641-2) contains supplementary material, which is available to authorized users.     

The User-Centered Design as Novel Perspective for Evaluating the Usability of BCI-Controlled Applications

Albeit research on brain-computer interfaces (BCI) for controlling applications has expanded tremendously, we still face a translational gap when bringing BCI to end-users. To bridge this gap, we adapted the user-centered design (UCD) to BCI research and development which implies a shift from focusing on single aspects, such as accuracy and information transfer rate (ITR), to a more holistic user experience. The UCD implements an iterative process between end-users and developers based on a valid evaluation procedure. Within the UCD framework usability of a device can be defined with regard to its effectiveness, efficiency, and satisfaction. We operationalized these aspects to evaluate BCI-controlled applications. Effectiveness was regarded equivalent to accuracy of selections and efficiency to the amount of information transferred per time unit and the effort invested (workload). Satisfaction was assessed with questionnaires and visual-analogue scales. These metrics have been successfully applied to several BCI-controlled applications for communication and entertainment, which were evaluated by end-users with severe motor impairment. Results of four studies, involving a total of N = 19 end-users revealed: effectiveness was moderate to high; efficiency in terms of ITR was low to high and workload low to medium; depending on the match between user and technology, and type of application satisfaction was moderate to high. The here suggested evaluation metrics within the framework of the UCD proved to be an applicable and informative approach to evaluate BCI controlled applications, and end-users with severe impairment and in the locked-in state were able to participate in this process.     

Ecological niche modeling re‐examined: A case study with the Darwin's fox

Many previous studies have attempted to assess ecological niche modeling performance using receiver operating characteristic (ROC) approaches, even though diverse problems with this metric have been pointed out in the literature. We explored different evaluation metrics based on independent testing data using the Darwin's Fox (Lycalopex fulvipes) as a detailed case in point. Six ecological niche models (ENMs; generalized linear models, boosted regression trees, Maxent, GARP, multivariable kernel density estimation, and NicheA) were explored and tested using six evaluation metrics (partial ROC, Akaike information criterion, omission rate, cumulative binomial probability), including two novel metrics to quantify model extrapolation versus interpolation (E‐space index I) and extent of extrapolation versus Jaccard similarity (E‐space index II). Different ENMs showed diverse and mixed performance, depending on the evaluation metric used. Because ENMs performed differently according to the evaluation metric employed, model selection should be based on the data available, assumptions necessary, and the particular research question. The typical ROC AUC evaluation approach should be discontinued when only presence data are available, and evaluations in environmental dimensions should be adopted as part of the toolkit of ENM researchers. Our results suggest that selecting Maxent ENM based solely on previous reports of its performance is a questionable practice. Instead, model comparisons, including diverse algorithms and parameterizations, should be the sine qua non for every study using ecological niche modeling. ENM evaluations should be developed using metrics that assess desired model characteristics instead of single measurement of fit between model and data. The metrics proposed herein that assess model performance in environmental space (i.e., E‐space indices I and II) may complement current methods for ENM evaluation.     

脑机接口中脑电信号提取方法和技术的研究进展

脑机接口(BCI)系统可以把大脑发出的信息直接转换成能够驱动外部设备的命令,并代替人的肢体或感觉器官实现人与外界的交流以及对外部环境的控制。BCI技术的发展目前还存在着很多问题,其中最关键的问题是必须有一个安全的、可长时间持续探测或者注射信号的方法。该文综述了当前BCI研究中不同脑电信号的提取方式特征以及信号记录装置,通过分析总结了其优缺点。对于各种不同信号方式的BCI,都有待于更多的科技工作者深入研究。     

Generic Information Can Retrieve Known Biological Associations: Implications for Biomedical Knowledge Discovery

Motivation

Weighted semantic networks built from text-mined literature can be used to retrieve known protein-protein or gene-disease associations, and have been shown to anticipate associations years before they are explicitly stated in the literature. Our text-mining system recognizes over 640,000 biomedical concepts: some are specific (i.e., names of genes or proteins) others generic (e.g., ‘Homo sapiens’). Generic concepts may play important roles in automated information retrieval, extraction, and inference but may also result in concept overload and confound retrieval and reasoning with low-relevance or even spurious links. Here, we attempted to optimize the retrieval performance for protein-protein interactions (PPI) by filtering generic concepts (node filtering) or links to generic concepts (edge filtering) from a weighted semantic network. First, we defined metrics based on network properties that quantify the specificity of concepts. Then using these metrics, we systematically filtered generic information from the network while monitoring retrieval performance of known protein-protein interactions. We also systematically filtered specific information from the network (inverse filtering), and assessed the retrieval performance of networks composed of generic information alone.

Results

Filtering generic or specific information induced a two-phase response in retrieval performance: initially the effects of filtering were minimal but beyond a critical threshold network performance suddenly drops. Contrary to expectations, networks composed exclusively of generic information demonstrated retrieval performance comparable to unfiltered networks that also contain specific concepts. Furthermore, an analysis using individual generic concepts demonstrated that they can effectively support the retrieval of known protein-protein interactions. For instance the concept “binding” is indicative for PPI retrieval and the concept “mutation abnormality” is indicative for gene-disease associations.

Conclusion

Generic concepts are important for information retrieval and cannot be removed from semantic networks without negative impact on retrieval performance.     

Influence of tree shape and evolutionary time‐scale on phylogenetic diversity metrics

During the last decades, describing, analysing and understanding the phylogenetic structure of species assemblages has been a central theme in both community ecology and macro‐ecology. Among the wide variety of phylogenetic structure metrics, three have been predominant in the literature: Faith's phylogenetic diversity (PD_Faith), which represents the sum of the branch lengths of the phylogenetic tree linking all species of a particular assemblage, the mean pairwise distance between all species in an assemblage (MPD) and the pairwise distance between the closest relatives in an assemblage (MNTD). Comparisons between studies using one or several of these metrics are difficult because there has been no comprehensive evaluation of the phylogenetic properties each metric captures. In particular it is unknown how PD_Faith relates to MDP and MNTD. Consequently, it is possible that apparently opposing patterns in different studies might simply reflect differences in metric properties. Here, we aim to fill this gap by comparing these metrics using simulations and empirical data. We first used simulation experiments to test the influence of community structure and size on the mismatch between metrics whilst varying the shape and size of the phylogenetic tree of the species pool. Second we investigated the mismatch between metrics for two empirical datasets (gut microbes and global carnivoran assemblages). We show that MNTD and PD_Faith provide similar information on phylogenetic structure, and respond similarly to variation in species richness and assemblage structure. However, MPD demonstrate a very different behaviour, and is highly sensitive to deep branching structure. We suggest that by combining complementary metrics that are sensitive to processes operating at different phylogenetic depths (i.e. MPD and MNTD or PD_Faith) we can obtain a better understanding of assemblage structure.     

Fuzzy Index to Evaluate Edge Detection in Digital Images

In literature, we can find different metrics to evaluate the detected edges in digital images, like Pratt''s figure of merit (FOM), Jaccard’s index (JI) and Dice’s coefficient (DC). These metrics compare two images, the first one is the reference edges image, and the second one is the detected edges image. It is important to mention that all existing metrics must binarize images before their evaluation. Binarization step causes information to be lost because an incomplete image is being evaluated. In this paper, we propose a fuzzy index (FI) for edge evaluation that does not use a binarization step. In order to process all detected edges, images are represented in their fuzzy form and all calculations are made with fuzzy sets operators and fuzzy Euclidean distance between both images. Our proposed index is compared to the most used metrics using synthetic images, with good results.     

Online Adaptation of a c-VEP Brain-Computer Interface(BCI) Based on Error-Related Potentials and Unsupervised Learning

The goal of a Brain-Computer Interface (BCI) is to control a computer by pure brain activity. Recently, BCIs based on code-modulated visual evoked potentials (c-VEPs) have shown great potential to establish high-performance communication. In this paper we present a c-VEP BCI that uses online adaptation of the classifier to reduce calibration time and increase performance. We compare two different approaches for online adaptation of the system: an unsupervised method and a method that uses the detection of error-related potentials. Both approaches were tested in an online study, in which an average accuracy of 96% was achieved with adaptation based on error-related potentials. This accuracy corresponds to an average information transfer rate of 144 bit/min, which is the highest bitrate reported so far for a non-invasive BCI. In a free-spelling mode, the subjects were able to write with an average of 21.3 error-free letters per minute, which shows the feasibility of the BCI system in a normal-use scenario. In addition we show that a calibration of the BCI system solely based on the detection of error-related potentials is possible, without knowing the true class labels.     

Comparison of Sensor Selection Mechanisms for an ERP-Based Brain-Computer Interface

A major barrier for a broad applicability of brain-computer interfaces (BCIs) based on electroencephalography (EEG) is the large number of EEG sensor electrodes typically used. The necessity for this results from the fact that the relevant information for the BCI is often spread over the scalp in complex patterns that differ depending on subjects and application scenarios. Recently, a number of methods have been proposed to determine an individual optimal sensor selection. These methods have, however, rarely been compared against each other or against any type of baseline. In this paper, we review several selection approaches and propose one additional selection criterion based on the evaluation of the performance of a BCI system using a reduced set of sensors. We evaluate the methods in the context of a passive BCI system that is designed to detect a P300 event-related potential and compare the performance of the methods against randomly generated sensor constellations. For a realistic estimation of the reduced system''s performance we transfer sensor constellations found on one experimental session to a different session for evaluation. We identified notable (and unanticipated) differences among the methods and could demonstrate that the best method in our setup is able to reduce the required number of sensors considerably. Though our application focuses on EEG data, all presented algorithms and evaluation schemes can be transferred to any binary classification task on sensor arrays.     

Conscious Brain-to-Brain Communication in Humans Using Non-Invasive Technologies

Human sensory and motor systems provide the natural means for the exchange of information between individuals, and, hence, the basis for human civilization. The recent development of brain-computer interfaces (BCI) has provided an important element for the creation of brain-to-brain communication systems, and precise brain stimulation techniques are now available for the realization of non-invasive computer-brain interfaces (CBI). These technologies, BCI and CBI, can be combined to realize the vision of non-invasive, computer-mediated brain-to-brain (B2B) communication between subjects (hyperinteraction). Here we demonstrate the conscious transmission of information between human brains through the intact scalp and without intervention of motor or peripheral sensory systems. Pseudo-random binary streams encoding words were transmitted between the minds of emitter and receiver subjects separated by great distances, representing the realization of the first human brain-to-brain interface. In a series of experiments, we established internet-mediated B2B communication by combining a BCI based on voluntary motor imagery-controlled electroencephalographic (EEG) changes with a CBI inducing the conscious perception of phosphenes (light flashes) through neuronavigated, robotized transcranial magnetic stimulation (TMS), with special care taken to block sensory (tactile, visual or auditory) cues. Our results provide a critical proof-of-principle demonstration for the development of conscious B2B communication technologies. More fully developed, related implementations will open new research venues in cognitive, social and clinical neuroscience and the scientific study of consciousness. We envision that hyperinteraction technologies will eventually have a profound impact on the social structure of our civilization and raise important ethical issues.     

Estimating the mutual information of an EEG-based Brain-Computer Interface.

An EEG-based Brain-Computer Interface (BCI) could be used as an additional communication channel between human thoughts and the environment. The efficacy of such a BCI depends mainly on the transmitted information rate. Shannon's communication theory was used to quantify the information rate of BCI data. For this purpose, experimental EEG data from four BCI experiments was analyzed off-line. Subjects imaginated left and right hand movements during EEG recording from the sensorimotor area. Adaptive autoregressive (AAR) parameters were used as features of single trial EEG and classified with linear discriminant analysis. The intra-trial variation as well as the inter-trial variability, the signal-to-noise ratio, the entropy of information, and the information rate were estimated. The entropy difference was used as a measure of the separability of two classes of EEG patterns.     

A consistent metric for nestedness analysis in ecological systems: reconciling concept and measurement

Nestedness has been widely reported for both metacommunities and networks of interacting species. Even though the concept of this ecological pattern has been well-defined, there are several metrics by which it can be quantified. We noted that current metrics do not correctly quantify two major properties of nestedness: (1) whether marginal totals (i.e. fills) differ among columns and/or among rows, and (2) whether the presences (1's) in less-filled columns and rows coincide, respectively, with those found in the more-filled columns and rows. We propose a new metric directly based on these properties and compare its behavior with that of the most used metrics, using a set of model matrices ranging from highly-nested to alternative structures in which no nestedness should be detected. We also used an empirical dataset to explore possible biases generated by the metrics as well as to evaluate correlations between metrics. We found that nestedness has been quantified by metrics that inappropriately detect this pattern, even for matrices in which there is no nestedness. In addition, the most used metrics are prone to type I statistical errors while our new metric has better statistical properties and consistently rejects a nested pattern for different types of random matrices. The analysis of the empirical data showed that two nestedness metrics, matrix temperature and the discrepancy measure, tend to overestimate the degrees of nestedness in metacommunities. We emphasize and discuss some implications of these biases for the theoretical understanding of the processes shaping species interaction networks and metacommunity structure.     

COMPARISON OF SIMPLE AND MULTIMETRIC DIATOM‐BASED INDICES FOR GREAT LAKES COASTLINE DISTURBANCE1

Because diatom communities are subject to the prevailing water quality in the Great Lakes coastal environment, diatom‐based indices can be used to support coastal‐monitoring programs and paleoecological studies. Diatom samples were collected from Great Lakes coastal wetlands, embayments, and high‐energy sites (155 sites), and assemblages were characterized to the species level. We defined 42 metrics on the basis of autecological and functional properties of species assemblages, including species diversity, motile species, planktonic species, proportion dominant taxon, taxonomic metrics (e.g., proportion Stephanodiscoid taxa), and diatom‐inferred (DI) water quality (e.g., DI chloride [Cl]). Redundant metrics were eliminated, and a diatom‐based multimetric index (MMDI) to infer coastline disturbance was developed. Anthropogenic stresses in adjacent coastal watersheds were characterized using geographic information system (GIS) data related to agricultural and urban land cover and atmospheric deposition. Fourteen independent diatom metrics had significant regressions with watershed stressor data; these metrics were selected for inclusion in the MMDI. The final MMDI was developed as the weighted sum of the selected metric scores with weights based on a metric’s ability to reflect anthropogenic stressors in the adjacent watersheds. Despite careful development of the multimetric approach, verification using a test set of sites indicated that the MMDI was not able to predict watershed stressors better than some of the component metrics. From this investigation, it was determined that simpler, more traditional diatom‐based metrics (e.g., DI Cl, proportion Cl‐tolerant species, and DI total phosphorus [TP]) provide superior prediction of overall stressor influence at coastal locales.     

Development and comparison of stream indices of biotic integrity using diatoms vs. non-diatom algae vs. a combination

Stream algal indices of biotic integrity (IBIs) are generally based entirely or largely on diatoms, because non-diatom (“soft”) algae can be difficult to quantify and taxonomically challenging, thus calling into question their practicality and cost-effectiveness for use as bioindicators. Little has been published rigorously evaluating the strengths of diatom vs. soft algae-based indices, or how they compare to indices combining these assemblages. Using a set of ranked evaluation criteria, we compare indices of biotic integrity (IBIs) (developed for southern California streams) that incorporate different combinations of algal assemblages. We split a large dataset into independent “calibration” and “validation” subsets, then used the calibration subset to screen candidate metrics with respect to degree of responsiveness to anthropogenic stress, metric score distributions, and signal-to-noise ratio. The highest-performing metrics were combined into a total of 25 IBIs comprising either single-assemblage metrics (based on either diatoms or soft algae, including cyanobacteria) or combinations of metrics representing the two assemblages (for “hybrid IBIs”). Performance of all IBIs was assessed based on: responsiveness to anthropogenic stress (in terms of surrounding land uses and a composite water-chemistry gradient) using the validation data, and evaluated based on signal-to-noise ratio, metric redundancy, and degree of indifference to natural gradients. Hybrid IBIs performed best overall based on our evaluation. Single-assemblage IBIs ranked lower than hybrids vis-à-vis the abovementioned performance attributes, but may be considered appropriate for routine monitoring applications. Trade-offs inherent in the use of the different algal assemblages, and types of IBI, should be taken into consideration when designing an algae-based stream bioassessment program.     

Brain-Computer Interface Speller System for Alternative Communication: A Review

Brain-computer interface (BCI) speller is a system that provides an alternative communication for the disable people. The brain wave is translated into machine command through a BCI speller which can be used as a communication medium for the patients to express their thought without any motor movement. A BCI speller aims to spell characters by using the electroencephalogram (EEG) signal. Several types of BCI spellers are available based on the EEG signal. A standard BCI speller system consists of the following elements: BCI speller paradigm, data acquisition system and signal processing algorithms. In this work, a systematic review is provided on the BCI speller system and it includes speller paradigms, feature extraction, feature optimization and classification techniques for BCI speller. The advantages and limitations of different speller paradigm and machine learning algorithms are discussed in this article. Also, the future research directions are discussed which can overcome the limitations of present state-of-the-art techniques for BCI speller.