No full-text available
To read the full-text of this research,
you can request a copy directly from the authors.
Classifying EEG Signals of Mind-Wandering Across Different Styles of Meditation
Abstract
In the modern world, it is easy to get lost in thought, partly because of the vast knowledge available at our fingertips via smartphones that divide our cognitive resources and partly because of our intrinsic thoughts. In this work, we aim to find the differences in the neural signatures of mind-wandering and meditation that are common across different meditative styles. We use EEG recording done during meditation sessions by experts of different meditative styles, namely shamatha, zazen, dzogchen, and visualization. We evaluate the models using the leave-one-out validation technique to train on three meditative styles and test the fourth left-out style. With this method, we achieve an average classification accuracy of above 70%, suggesting that EEG signals of meditation techniques have a unique neural signature across meditative styles and can be differentiated from mind-wandering states. In addition, we generate lower-dimensional embeddings from higher-dimensional ones using t-SNE, PCA, and LLE algorithms and observe visual differences in embeddings between meditation and mind-wandering. We also discuss the general flow of the proposed design and contributions to the field of neuro-feedback-enabled mind-wandering detection and correction devices.KeywordsMeditationMind-wanderingClassificationMachine learningDeep learningCognitionNeuro-feedbackEEG
... To address these limitations, we propose a novel class of methods for personalized learning from minimal subject-specific data, enabling state quantification without requiring subjects to master a certain desirable state. This ability to learn from a single data category allows the method presented below to be used on data from novice meditators, for practices without a fixed 'end goal' , for neurofeedback, and in many other settings where substantial data on a target state may be unavailable-unlike existing work on trying to automatically acquire models of meditative states using machine learning [19][20][21][22][23][24][25][26][27] , which all require data from at least two different states (e.g. an undesirable and a desirable state) to be trained and make predictions. ...
With mounting evidence for the benefits of meditation, there has been a growing interest in measuring and quantifying meditative states. This study introduces the Inner Dereification Index (IDI), a class of personalized models designed to quantify the distance from non-meditative states such as mind wandering based on a single individual’s neural activity. In addition to demonstrating high classification accuracy (median AUC: 0.996) at distinguishing meditation from thinking states moment by moment, IDI can accurately stratify meditator cohorts by experience, and correctly identify the practices most effective at training the dereification aspect of meditation (decentering from immersion with thoughts and perceptions and recognizing them as mental constructs). These results suggest that IDI models may be a useful real-time proxy for dereification and meditation progress, requiring only 1 min of mind wandering data (and no meditation data) during model training. Thus, they show promise for applications such as real-time meditation feedback, progress tracking, personalization of practices, and potential therapeutic applications of neurofeedback-assisted generation of positive states of consciousness.
... Researchers have also used feature engineering and machine learning approaches to classify brain states. They have used features such as power spectral density [8] and spectral coherence [34] as inputs to classical machine learning classifiers for the task. The accuracy of MI-BCI systems is affected by challenges such as low signal-to-noise ratio (SNR), and neuroplasticity [37]. ...
... The discovery of patterns that can be used in systems to guide naive practitioners brings enormous opportunities for cognitive, signal processing, and machine learning scientists. Along with this, mind-wandering detection is an interesting research area for feature engineering [8]. ...
The brain is an incredibly complex organ capable of perceiving and interpreting a wide range of stimuli. Depending on individual brain chemistry and wiring, different people decipher the same stimuli differently, conditioned by their life experiences and environment. This study’s objective is to decode how the CNN models capture and learn these differences and similarities in brain waves using three publicly available EEG datasets. While being exposed to a variety of media stimuli, each brain produces unique brain waves with some similarity to other neural signals to the same stimuli. However, to figure out whether our neural models are able to interpret and distinguish the common and unique signals correctly, we employed three widely used CNN architectures to interpret brain signals. We extracted the pre-processed versions of the EEG data and identified the dependency of time windows on feature learning for song and movie classification tasks, along with analyzing the performance of models on each dataset. While the minimum length snippet of 5 s was enough for the personalized model, the maximum length snippet of 30 s proved to be the most efficient in the case of the generalized model. The usage of a deeper architecture, i.e., DeepConvNet was found to be the best for extracting personalized and generalized features with the NMED-T and SEED datasets. However, EEGNet gave a better performance on the NMED-H dataset. Maximum accuracy of 69%, 100%, and 56% was achieved in the case of the personalized model on NMED-T, NMED-H, and SEED datasets, respectively. However, the maximum accuracies dropped to 18%, 37%, and 14% on NMED-T, NMED-H, and SEED datasets, respectively, in the generalized model. We achieved a 5% improvement over the state of the art while examining shared experiences on NMED-T. This marked the out-of-distribution generalization problem and signified the role of individual differences in media perception, thus emphasizing the development of personalized models along with generalized models with shared features at a certain level.
In this study, we examined EEG analysis techniques across a variety of meditation traditions in order to identify reliable metrics that could be applied in meditation research, revealing how each tradition interprets eeg signals distinctly. The study’s potential is in its future neurotechnological innovations, to increase usage of meditation (by enriching one’s internal environment for better equilibration) among users. EEG's high temporal resolution may result in misinterpretation or erroneous correlation if the analyzing technique is unreliable and weak. Overall, investigation of this may provide insight into the complex
nature of meditative practice and its impact on the brain. Methods: Neuroscientific studies demonstrate several methods from simple to complex, including spectral power, entropy (sample, lempel-ziv), and fractal dimensions (higuchi) etc. Distinguishing expert and naive practitioners involve large-scale dynamics of distinct cognitive and resource allocation across different meditation types. Meditation research includes a comparison of expert meditators with controls, Intervariability across meditation practitioners (Himalayan yoga, Vipassana, etc) with controls. There have been several studies conducted on the
effects of mind-wandering on brain rhythms and meditation practice among expert meditators and controls, using thought probes, instructed mind-wandering conditions. Results: Meditation-related EEG studies have shown power increases in theta and alpha bands and overall frequency slowing, with the occasional increase in gamma power. Large scale decrease in entropy (Lempel Ziv-Complexity) during meditation states was observed. Contrary to this finding, a study by Vivot et al., 2020 observed increased alpha and gamma power sample entropy across vipassana meditators. Decreased number of transient alphatheta 2:1 harmonic ratio during meditation conditions among 43 experienced meditators, was revealed. In one study, after Integrated Body-Mind Training (IBMT) of 24 participants, functional connectivity measures were performed. The IBMT group
exhibited a larger clustering coefficient, global and local efficiency, and shorter average path length at midline electrodes when compared to controls. Discussion: The generation of a neurophysiological marker that is reliable when a person is progressing
from one level of meditation to another is still in its infancy. Depending on how different meditation styles are studied and analyzed there might be both similarities and differences in the results, but rigorous scrutiny (preprocessing, experimental design, meditation type, feature extraction, etc.) will provide a better insight into generalizations.
Previous studies showed that entrainment of light flicker at low gamma frequencies provided neuroprotection in mouse models of Alzheimer’s disease (AD) and stroke. The current study was set to explore the feasibility of using 40 Hz light flicker for human brain stimulation for future development as a tool for brain disease treatment. The effect of 40 Hz low gamma frequency light on a cohort of healthy human brains was examined using 64 channel electroencephalography (EEG), followed by microstate analyses. A random frequency light flicker was used as a negative control treatment. Light flicker at 40 Hz significantly increased the corresponding band power in the O1, Oz, and O3 electrodes covering the occipital areas of both sides of the brain, indicating potent entrainment with 40 Hz light flicker in the visual cortex area. Importantly, the 40 Hz light flicker significantly altered microstate coverage, transition duration, and the Lempel-Ziv complexity (LZC) compared to the rest state. Microstate metrics are known to change in the brains of Alzheimer’s disease, schizophrenia, and stroke patients. The current study laid the foundation for the future development of 40 Hz light flicker as therapeutics for brain diseases.
The clinical and societal measurement of human sleep has increased exponentially in recent years. However, unlike other fields of medical analysis that have become highly automated, basic and clinical sleep research still relies on human visual scoring. Such human-based evaluations are time-consuming, tedious, and can be prone to subjective bias. Here, we describe a novel algorithm trained and validated on +30,000 hr of polysomnographic sleep recordings across heterogeneous populations around the world. This tool offers high sleep-staging accuracy that matches human scoring accuracy and interscorer agreement no matter the population kind. The software is designed to be especially easy to use, computationally low-demanding, open source, and free. Our hope is that this software facilitates the broad adoption of an industry-standard automated sleep staging software package.
Mind wandering is often characterized by attention oriented away from an external task towards our internal, self-generated thoughts. This universal phenomenon has been linked to numerous disruptive functional outcomes, including performance errors and negative affect. Despite its prevalence and impact, studies to date have yet to identify robust behavioral signatures, making unobtrusive, yet reliable detection of mind wandering a difficult but important task for future applications. Here we examined whether electrophysiological measures can be used in machine learning models to accurately predict mind wandering states. We recorded scalp EEG from participants as they performed an auditory target detection task and self-reported whether they were on task or mind wandering. We successfully classified attention states both within (person-dependent) and across (person-independent) individuals using event-related potential (ERP) measures. Non-linear and linear machine learning models detected mind wandering above-chance within subjects: support vector machine (AUC = 0.715) and logistic regression (AUC = 0.635). Importantly, these models also generalized across subjects: support vector machine (AUC = 0.613) and logistic regression (AUC = 0.609), suggesting we can reliably predict a given individual’s attention state based on ERP patterns observed in the group. This study is the first to demonstrate that machine learning models can generalize to “never-seen-before” individuals using electrophysiological measures, highlighting their potential for real-time prediction of covert attention states.
Meditation is an umbrella term for a number of mental training practices designed to improve the monitoring and regulation of attention and emotion. Some forms of meditation are now being used for clinical intervention. To accompany the increased clinical interest in meditation, research investigating the neural basis of these practices is needed. A central hypothesis of contemplative neuroscience is that meditative states, which are unique on a phenomenological level, differ on a neurophysiological level. To identify the electrophysiological correlates of meditation practice, the electrical brain activity of highly skilled meditators engaging in one of six meditation styles (shamatha, vipassana, zazen, dzogchen, tonglen, and visualization) was recorded. A mind-wandering task served as a control. Lempel–Ziv complexity showed differences in nonlinear brain dynamics (entropy) during meditation compared with mind wandering, suggesting that meditation, regardless of practice, affects neural complexity. In contrast, there were no differences in power spectra at six different frequency bands, likely due to the fact that participants engaged in different meditation practices. Finally, exploratory analyses suggest neurological differences among meditation practices. These findings highlight the importance of studying the electroencephalography (EEG) correlates of different meditative practices.
Previous research has shown that mind wandering has both positive and negative effects. Mind wandering may improve creative problem solving; however, it could also lead to negative moods and poor mental health. It has also been shown that some forms of mental illness are positively related to creativity. However, the three factors of mind wandering, divergent thinking, and mental health have not been examined simultaneously, so it is possible that these relationships are manifested by spurious correlations. Therefore, we examined the relations among the three factors while controlling for each of their confounding effects. We asked 865 participants (458 men, 390 women, 17 unknown; Mage = 18.99 years, SD = 1.16) to complete a questionnaire measuring mind wandering traits, divergent thinking, and mental health measures including depressive symptoms and schizotypal personality. Multiple regression analysis showed that people who reported more depressive symptoms, schizotypal personality, and divergent thinking, were more likely to engage in mind-wandering. Our results indicated that frequency of mind wandering was linked to a risk of poorer mental health as well as to higher divergent thinking ability. In future research, we will examine the features of mind wandering related to divergent thinking and mental health by considering the contents of wandering thoughts and whether they are ruminative or not. We also need to examine whether the same results will be found when studying professionals in creative occupations, and when using different scoring methods in divergent thinking tests.
We address the hypothesis that the entropy of neural dynamics indexes the intensity and quality of conscious content. Previous work established that serotonergic psychedelics can have a dysregulating effect on brain activity, leading to subjective effects that present a considerable overlap with the phenomenology of certain meditative states. Here we propose that the prolonged practice of meditation results in endogenous increased entropy of brain oscillatory activity. We estimated the entropy of band-specific oscillations during the meditative state of traditions classified as 'focused attention' (Himalayan Yoga), 'open monitoring' (Vipassana), and 'open awareness' (Isha Shoonya Yoga). Among all traditions, Vipassana resulted in the highest entropy increases, predominantly in the alpha and low/high gamma bands. In agreement with previous studies, all meditation traditions increased the global coherence in the gamma band, but also stabilized gamma-range dynamics by lowering the metastability. Finally, machine learning classifiers could successfully generalize between certain pairs of meditation traditions based on the scalp distribution of gamma band entropies. Our results extend previous findings on the spectral changes observed during meditation, showing how long-term practice can lead to the capacity for achieving brain states of high entropy. This constitutes an example of an endogenous, self-induced high entropy state.
Rapid advancement in the hardware based technologies over past decades opened up new possibilities for Biological and Life scientists to gather multimodal data from various application domains (e.g., Omics, Bioimaging, Medical Imaging, and [Brain/Body]-Machine Interfaces). Novel data intensive machine learning techniques are required to decipher these data. Recent research in Deep learning (DL), Reinforcement learning (RL), and their combination (Deep RL) promise to revolutionize Artificial Intelligence. Increasing computational power, faster data storage devices, and declining computing costs allowed scientists to apply these techniques on such enormous and complex datasets which otherwise would not have been possible. This review article provides a comprehensive survey of the applications of DL, RL, and Deep RL techniques in mining Biological data coming from various application domains. In addition, the performances of DL techniques when applied to different datasets pertaining to the various application domains have been compared. Finally, it outlines some open issues on this challenging research area and postulates possible future perspectives.
Although empirical interest in meditation has flourished in recent years, few studies have addressed possible downsides of meditation practice, particularly in community populations. In-depth interviews were conducted with 30 male meditators in London, UK, recruited using principles of maximum variation sampling, and analysed using a modified constant comparison approach. Having originally set out simply to inquire about the impact of various meditation practices (including but not limited to mindfulness) on men’s wellbeing, we uncovered psychological challenges associated with its practice. While meditation was generally reported to be conducive to wellbeing, substantial difficulties accounted for approximately one quarter of the interview data. Our paper focuses specifically on these issues in order to alert health professionals to potential challenges associated with meditation. Four main problems of increasing severity were uncovered: Meditation was a difficult skill to learn and practise; participants encountered troubling thoughts and feelings which were hard to manage; meditation reportedly exacerbated mental health issues, such as depression and anxiety; and in a few cases, meditation was associated with psychotic episodes. Our paper raises important issues around safeguarding those who practise meditation, both within therapeutic settings and in the community.
Magnetoencephalography and electroencephalography (M/EEG) measure the weak electromagnetic signals generated by neuronal activity in the brain. Using these signals to characterize and locate neural activation in the brain is a challenge that requires expertise in physics, signal processing, statistics, and numerical methods. As part of the MNE software suite, MNE-Python is an open-source software package that addresses this challenge by providing state-of-the-art algorithms implemented in Python that cover multiple methods of data preprocessing, source localization, statistical analysis, and estimation of functional connectivity between distributed brain regions. All algorithms and utility functions are implemented in a consistent manner with well-documented interfaces, enabling users to create M/EEG data analysis pipelines by writing Python scripts. Moreover, MNE-Python is tightly integrated with the core Python libraries for scientific comptutation (NumPy, SciPy) and visualization (matplotlib and Mayavi), as well as the greater neuroimaging ecosystem in Python via the Nibabel package. The code is provided under the new BSD license allowing code reuse, even in commercial products. Although MNE-Python has only been under heavy development for a couple of years, it has rapidly evolved with expanded analysis capabilities and pedagogical tutorials because multiple labs have collaborated during code development to help share best practices. MNE-Python also gives easy access to preprocessed datasets, helping users to get started quickly and facilitating reproducibility of methods by other researchers. Full documentation, including dozens of examples, is available at http://martinos.org/mne.
This study examined the relationship between wandering mind, depression and mindfulness. We used the Sustained Attention to Response Task to assess the wandering mind, while the online thought probes were employed as the subjective marker for mind-wandering. The Beck Depression Inventory and Mindfulness Attention and Awareness Scale were used to assess depression and dispositional mindfulness respectively. The results revealed that the wandering mind even without awareness was not only positively associated with depression, but also negatively related to dispositional mindfulness. Depression was negatively related to dispositional mindfulness. These results might provide evidence that a wandering mind is positively associated with depression and mindfulness.
Substantial evidence suggests that mind-wandering typically occurs at a significant cost to performance. Mind-wandering-related deficits in performance have been observed in many contexts, most notably reading, tests of sustained attention, and tests of aptitude. Mind-wandering has been shown to negatively impact reading comprehension and model building, impair the ability to withhold automatized responses, and disrupt performance on tests of working memory and intelligence. These empirically identified costs of mind-wandering have led to the suggestion that mind-wandering may represent a pure failure of cognitive control and thus pose little benefit. However, emerging evidence suggests that the role of mind-wandering is not entirely pernicious. Recent studies have shown that mind-wandering may play a crucial role in both autobiographical planning and creative problem solving, thus providing at least two possible adaptive functions of the phenomenon. This article reviews these observed costs and possible functions of mind-wandering and identifies important avenues of future inquiry. (PsycINFO Database Record (c) 2013 APA, all rights reserved).
Today’s fast paced life reports so much stress among people that it may lead to various psychological and physical illnesses. Yoga and meditation are the best strategies to reduce the effect of stress on physical and mental level without any side-effects. In this study, combined yoga and Sudarshan Kriya (SK) has been used as an alternative and complementary therapy for the management of stress. The aim of the study is to find a method to classify the meditator and non-meditator states with the best accuracy. The 50 subjects have been participating in this study and divided into two groups, i.e. study and control group. The subjects with regular practice of Yoga and SK are known as meditators and the ones without any practice of yoga and meditation were known as non-meditators. Electroencephalogram (EEG) signals were acquired from these both groups before and after 3 months. The statistical parameters were computed from these acquired EEG signals using Discrete Wavelet Transform (DWT). These extracted statistical parameters were given as input to the classifiers. The decision tree, discriminant analysis, logistic regression, Support Vector Machine (SVM), Weighted K- Nearest Neighbour (KNN) and ensemble classifiers were used for classification of meditator and non- meditator states from the acquired EEG signals. The results have demonstrated that the SVM method gives the highest classification accuracy as compared to other classifiers. The proposed method can be used as a diagnosis system in clinical practices.
Recent developments in neurotechnology effectively utilize the decades of neuroscientific findings of multiple meditation techniques. Meditation is linked to higher-order cognitive processes, which may function as a scaffold for cognitive control. In line with these developments, we analyze oscillatory brain activities of expert and non-expert meditators from the Himalayan Yoga tradition. We exploit four dimensions (Temporal, Spectral, Spatial and Pattern) of EEG data and present an analysis pipeline employing machine learning techniques. We discuss the significance of different frequency bands in relation with distinct primary 5 scalp brain regions. Functional connectivity networks (PLV) are utilized to generate features for classification between expert and non-expert meditators. We find (a) higher frequency β and γ oscillations generate maximum discrimination over the parietal region whereas lower frequency θ and α oscillations dominant over the frontal region; (b) maximum accuracy of over 90% utilizing features from all regions; (c) Quadratic Discriminant Analysis surpasses other classifiers by learning distribution for classification. Overall, this paper contributes a pipeline to analyze EEG data utilizing various properties and suggests potential neural markers for an expert meditative state. We discuss the implications of our research for the advancement of personalized headset design that rely on feedback on depth of meditation by learning from expert meditators.
Several Convolutional Deep Learning models have been proposed to classify the cognitive states utilizing several neuro-imaging domains. These models have achieved significant results, but they are heavily designed with millions of parameters, which increases train and test time, making the model complex and less suitable for real-time analysis. This paper proposes a simple, lightweight CNN model to classify cognitive states from Electroencephalograph (EEG) recordings. We develop a novel pipeline to learn distinct cognitive representation consisting of two stages. The first stage is to generate the 2D spectral images from neural time series signals in a particular frequency band. Images are generated to preserve the relationship between the neighboring electrodes and the spectral property of the cognitive events. The second is to develop a time-efficient, computationally less loaded, and high-performing model. We design a network containing 4 blocks and major components include standard and depth-wise convolution for increasing the performance and followed by separable convolution to decrease the number of parameters which maintains the tradeoff between time and performance. We experiment on open access EEG meditation dataset comprising expert, nonexpert meditative, and control states. We compare performance with six commonly used machine learning classifiers and four state of the art deep learning models. We attain comparable performance utilizing less than 4% of the parameters of other models. This model can be employed in a real-time computation environment such as neurofeedback.
Objectives
The present investigation is to study the impact of yoga and meditation on Brain waves concerning physical and mental health. There are mainly three stages (steps) in the brain wave classification:(i) preprocessing, ii) feature extraction, and iii) classification. This work provides a review of interpretation methods of Brain signals (Electroencephalogram (EEG)) EEG during yoga and meditation. Past research has revealed significant mental and physical advantages with yoga and meditation (1).
Methods
The research topic reviewed focused on the machine learning strategies applied for the interpretation of brain waves. In addressing the research questions highlighted earlier in the general introduction, we conducted a systematic search of articles from targeted scientific and journal online databases that included PubMed, Web of Science, IEEE Xplore Digital Library (IEEE), and Arxiv databases based on their relevance to the research questions and domain topic. The survey topic is relatively nascent, and therefore, the scope of the search period was limited to the 20-year timeline that was deemed representative of the research topic under investigation. The literature search was based on the keywords “EEG”, “yoga*” and “meditation*”. The key phrases were concatenated using Boolean expressions and applied to search through the selected online databases yielding a total of 120 articles. The online databases were selected based on the relevancy of content with the research title, research questions, and the domain application. The literature review search, process, and classification were carefully conducted guided by two defined measures; 1.) Inclusion criteria; and 2.) Exclusion criteria. These measures define the criteria for searching and extracting relevant articles relating to the research title and domain of interest.
Results
Our literature search and review indicate a broad spectrum of neural mechanics under a variety of meditation styles have been investigated. A detailed analysis of various mental states using Zen, CHAN, mindfulness, TM, Rajayoga, Kundalini, Yoga, and other meditation styles have been described by means of EEG bands. Classification of mental states using KNN, SVM, Random forest, Fuzzy logic, neural networks, Convolutional Neural Networks has been described. Superior research is still required to classify the EEG signatures corresponding to different mental states.
Conclusions
Yoga practice may be an effective adjunctive treatment for a clinical and aging population. Advanced research can examine the effects of specific branches of yoga on a designated clinical grouping. Yoga and meditation increased overall healthy brain activity (2).
EEG oscillatory correlates of expert meditators have been studied in the time-frequency domain. Machine Learning techniques are required to expand the understanding of oscillatory signatures. In this work, we propose a methodological pipeline to develop machine learning models for the classification between expert and nonexpert meditative state. We carried out this study utilizing the online repository consisting of EEG dataset of 24 meditators that categorized as 12 experts and 12 nonexperts meditators. The pipeline consists of four stages that include feature engineering, machine learning classifiers, feature selection, and visualization. We decomposed signals using five wavelet families consisting of Haar, Biorthogonal(1.3-6.8), Daubechies( orders 2-10), Coiflet(orders 1-5), and Symlet(2-8), followed by feature extraction using relative entropy and power. We classified the meditative state between expert and non-expert meditators employing twelve classifiers to build machine learning models. Wavelet coefficients d8 shows the maximum classification accuracy in all the wavelet families. Wavelet orders Bior3.5 and Coif3 produce the maximum classification performance with the detail coefficient d8 using relative power. We have successfully classified the meditative state between expert and non-expert with 100% accuracy using d5,d6,d7,d8,a8 coefficients. Multi-Layer Perceptron and Quadratic Discriminant Analysis attain the highest accuracy. We have figured out the most discriminating channels during classification and reported 20 channels involving frontal, central and parietal regions. We plot the high dimensional structure of data by utilizing two feature reduction techniques PCA and t-SNE.
Despite widespread adoption, machine learning models remain mostly black boxes. Understanding the reasons behind predictions is, however, quite important in assessing trust, which is fundamental if one plans to take action based on a prediction, or when choosing whether to deploy a new model. Such understanding also provides insights into the model, which can be used to transform an untrustworthy model or prediction into a trustworthy one.
In this work, we propose LIME, a novel explanation technique that explains the predictions of any classifier in an interpretable and faithful manner, by learning an interpretable model locally varound the prediction. We also propose a method to explain models by presenting representative individual predictions and their explanations in a non-redundant way, framing the task as a submodular optimization problem. We demonstrate the flexibility of these methods by explaining different models for text (e.g. random forests) and image classification (e.g. neural networks). We show the utility of explanations via novel experiments, both simulated and with human subjects, on various scenarios that require trust: deciding if one should trust a prediction, choosing between models, improving an untrustworthy classifier, and identifying why a classifier should not be trusted.
Due to an extensive list of restraints, brain-computer interface (BCI) technology has seen limited success outside of laboratory conditions. In order to address these limitations, which have prevented widespread deployment, an existing modular architecture has been adapted to support hybrid collaboration of commercially available BCI and eye tracking technologies. However, combining multiple input modalities, which have different temporal properties, presents a challenge in terms of data fusion and collaboration at the user interface. The use of cost-effective and readily available equipment will further promote hybrid BCI as a viable but alternative interface for human computer interaction. In this paper, we focus on navigation through a virtual smart home and control of devices within the rooms; the navigation being controlled by multimodal interaction. As such, it promises a better information transfer rate than BCI alone. Consequently, an extended architecture for a personalised hybrid BCI system has been proposed.
We introduce Adam, an algorithm for first-order gradient-based optimization
of stochastic objective functions. The method is straightforward to implement
and is based an adaptive estimates of lower-order moments of the gradients. The
method is computationally efficient, has little memory requirements and is well
suited for problems that are large in terms of data and/or parameters. The
method is also ap- propriate for non-stationary objectives and problems with
very noisy and/or sparse gradients. The method exhibits invariance to diagonal
rescaling of the gradients by adapting to the geometry of the objective
function. The hyper-parameters have intuitive interpretations and typically
require little tuning. Some connections to related algorithms, on which Adam
was inspired, are discussed. We also analyze the theoretical convergence
properties of the algorithm and provide a regret bound on the convergence rate
that is comparable to the best known results under the online convex
optimization framework. We demonstrate that Adam works well in practice when
experimentally compared to other stochastic optimization methods.
Many areas of science depend on exploratory data analysis and visualization. The need to analyze large amounts of multivariate
data raises the fundamental problem of dimensionality reduction: how to discover compact representations of high-dimensional
data. Here, we introduce locally linear embedding (LLE), an unsupervised learning algorithm that computes low-dimensional,
neighborhood-preserving embeddings of high-dimensional inputs. Unlike clustering methods for local dimensionality reduction,
LLE maps its inputs into a single global coordinate system of lower dimensionality, and its optimizations do not involve local
minima. By exploiting the local symmetries of linear reconstructions, LLE is able to learn the global structure of nonlinear
manifolds, such as those generated by images of faces or documents of text.
Visualizing data using t-sne
- L Van Der Maaten
- G Hinton
Van der Maaten, L., Hinton, G.: Visualizing data using t-sne. Journal of machine
learning research 9(11) (2008)