Single-Trial Decoding of Scalp EEG under Natural Conditions

There is significant current interest in decoding mental states from electroencephalography (EEG) recordings. EEG signals are subject-specific, are sensitive to disturbances, and have a low signal-to-noise ratio, which has been mitigated by the use of laboratory-grade EEG acquisition equipment under highly controlled conditions. In the present study, we investigate single-trial decoding of natural, complex stimuli based on scalp EEG acquired with a portable, 32 dry-electrode sensor system in a typical office setting. We probe generalizability by a leave-one-subject-out cross-validation approach. We demonstrate that support vector machine (SVM) classifiers trained on a relatively small set of denoised (averaged) pseudotrials perform on par with classifiers trained on a large set of noisy single-trial samples. We propose a novel method for computing sensitivity maps of EEG-based SVM classifiers for visualization of EEG signatures exploited by the SVM classifiers. Moreover, we apply an NPAIRS resampling framework for estimation of map uncertainty, and thus show that effect sizes of sensitivity maps for classifiers trained on small samples of denoised data and large samples of noisy data are similar. Finally, we demonstrate that the average pseudotrial classifier can successfully predict the class of single trials from withheld subjects, which allows for fast classifier training, parameter optimization, and unbiased performance evaluation in machine learning approaches for brain decoding.

Download Full-text

Single-Trial Decoding of Scalp EEG Under Natural Conditions

10.1101/481630 ◽

2018 ◽

Author(s):

Greta Tuckute ◽

Sofie Therese Hansen ◽

Nicolai Pedersen ◽

Dea Steenstrup ◽

Lars Kai Hansen

Keyword(s):

Signal To Noise Ratio ◽

Mental States ◽

Small Samples ◽

Support Vector ◽

Large Set ◽

Learning Approaches ◽

Single Trial ◽

Scalp Eeg ◽

Dry Electrode ◽

Sensitivity Maps

ABSTRACTThere is significant current interest in decoding mental states from electro-encephalography (EEG) recordings. EEG signals are subject-specific, sensitive to disturbances, and have a low signal-to-noise ratio, which has been mitigated by the use of laboratory-grade EEG acquisition equipment under highly controlled conditions. In the present study, we investigate single-trial decoding of natural, complex stimuli based on scalp EEG acquired with a portable, 32 dry-electrode sensor system in a typical office setting. We probe generalizability by a leave-one-subject-out cross-validation approach. We demonstrate that Support Vector Machine (SVM) classifiers trained on a relatively small set of de-noised (averaged) pseudo-trials perform on par with classifiers trained on a large set of noisy single-trial samples. For visualization of EEG signatures exploited by SVM classifiers, we propose a novel method for computing sensitivity maps of EEG-based SVM classifiers. Moreover, we apply the NPAIRS resampling framework for estimation of map uncertainty and show that effect sizes of sensitivity maps for classifiers trained on small samples of de-noised data and large samples of noisy data are similar. Finally, we demonstrate that the average pseudo-trial classifier can successfully predict the class of single trials from withheld subjects, which allows for fast classifier training, parameter optimization and unbiased performance evaluation in machine learning approaches for brain decoding.

Download Full-text

Using a machine learning approach to complement group level statistics in experimental psychology: A case study to reveal different levels of inhibition in a modified Flanker Task

10.1101/502278 ◽

2018 ◽

Author(s):

Tanja Krumpe ◽

Christian Scharinger ◽

Wolfgang Rosenstiel ◽

Peter Gerjets ◽

Martin Spueler

Keyword(s):

Machine Learning ◽

Executive Function ◽

Inhibitory Control ◽

Flanker Task ◽

Mental States ◽

Support Vector ◽

Group Level ◽

Single Trial ◽

Level Statistics ◽

Different Levels

In this paper, we demonstrate how machine learning (ML) can be used to beneficially complement the traditional analysis of behavioral and physiological data to provide new insights into the structure of mental states, in this case, executive functions (EFs) with a focus on inhibitory control. We used a modified Flanker task with the aim to distinguish three levels of inhibitory control: no inhibition, readiness for inhibition and the actual execution of inhibitory control. A simultaneously presented n-back task was used to additionally induce demands on a second executive function. This design enabled us to investigate how the overlap of resources influences the distinction between three levels of inhibitory control. A support vector machine (SVM) based classification approach has been used on EEG data to predict the level of inhibitory control on single-subject and single-trial level. The SVM classification is a subject-specific and single-trial based approach which will be compared to standard group-level statistical approaches to reveal that both methodologies access different properties of the data. We show that considering both methods can give new insights into mental states which cannot be discovered when only using group-level statistics alone. Machine learning results indicate that three different levels of inhibitory control can be distinguished, while the group-average analysis does not give rise to this assumption. In addition, we highlight one other important benefit of the ML approach. We are able to define specific properties of the executive function inhibition by investigating the neural activation patterns that were used during the classification process.

Download Full-text

FATIGUE DETECTION USING THE STRENGTH OF DOMINANT EEG SOURCE: A BEAMFORMING APPROACH

Biomedical Engineering Applications Basis and Communications ◽

10.4015/s1016237218500230 ◽

2018 ◽

Vol 30 (03) ◽

pp. 1850023 ◽

Cited By ~ 1

Author(s):

Samaneh Kouchaki ◽

Reza Boostani ◽

Fatemeh Razavipour

Keyword(s):

Nearest Neighbor ◽

Mental States ◽

Minimum Variance ◽

Support Vector ◽

Svm Classifier ◽

Scalp Eeg ◽

Discriminative Feature ◽

Before And After ◽

Fatigue Detection ◽

Eeg Features

It is evident that the electroencephalogram (EEG) rhythms are slightly changed when the efficacy of mental activity declines (brain fatigue). Nonetheless, this slight change is not easily detectable by the so far suggested scalp EEG features. The goal of this paper is to propose an EEG-based biomarker, which has a congruity to the mental fatigue variation to detect the transition from non-fatigue to the fatigue mental state. The strength of the dominant EEG source, extracted by minimum variance beamformer (MVB), is proposed here as a discriminative feature to remarkably classify the two mental states. To assess the proposed scheme, EEG signals of 17 volunteers were recorded via 32 electrodes before and after taking an exhausting mental exam (3[Formula: see text]h) and the extracted EEG features were labeled as non-fatigue and fatigue, respectively. After removing the eye-blink effect, the proposed feature along with the conventional EEG features were extracted from the recorded EEGs and then applied to support vector machine (SVM) and 1-nearest neighbor (1NN) classifiers in order to differentiate these two mental states. The best result is achieved by applying the proposed feature to the SVM classifier providing 97.06% classification accuracy which is significantly ([Formula: see text]) superior to its counter parts.

Download Full-text

Baby Cry Detection: Deep Learning and Classical Approaches

10.31234/osf.io/p8xgm ◽

2019 ◽

Author(s):

Rami Cohen ◽

Dima Ruinskiy ◽

Janis Zickfeld ◽

Hans IJzerman ◽

Yizhar Lavner

Keyword(s):

Neural Network ◽

Deep Learning ◽

Social Research ◽

Signal To Noise Ratio ◽

Support Vector ◽

Temporal Behavior ◽

Learning Approaches ◽

Signal To Noise ◽

Vector Machines ◽

Domestic Environments

In this chapter, we compare deep learning and classical approaches for detection of baby cry sounds in various domestic environments under challenging signal-to-noise ratio conditions. Automatic cry detection has applications in commercial products (such as baby remote monitors) as well as in medical and psycho-social research. We design and evaluate several convolutional neural network (CNN) architectures for baby cry detection, and compare their performance to that of classical machine-learning approaches, such as logistic regression and support vector machines. In addition to feed-forward CNNs, we analyze the performance of recurrent neural network (RNN) architectures, which are able to capture temporal behavior of acoustic events. We show that by carefully designing CNN architectures with specialized non-symmetric kernels, better results are obtained compared to common CNN architectures.

Download Full-text

A Comparison of fMRI and Behavioral Models for Predicting Inter-Temporal Choices

10.1101/866285 ◽

2019 ◽

Author(s):

Felix G. Knorr ◽

Philipp T. Neukam ◽

Juliane H. Fröhner ◽

Holger Mohr ◽

Michael N. Smolka ◽

...

Keyword(s):

Cross Validation ◽

Signal To Noise Ratio ◽

Brain Activity ◽

Behavioral Model ◽

Support Vector ◽

Behavioral Models ◽

Single Trial ◽

Subjective Value ◽

The Brain ◽

Time Point

AbstractIn an inter-temporal choice (IteCh) task, subjects are offered a smaller amount of money immediately or a larger amount at a later time point. Here, we are using trial-by-trial fMRI data from 363 recording sessions and machine learning in an attempt to build a classifier that would ideally outperform established behavioral model given that it has access to brain activity specific to a single trial. Such methods could allow for future investigations of state-like factors that influence IteCh choices.To investigate this, coefficients of a GLM with one regressor per trial were used as features for a support vector machine (SVM) in combination with a searchlight approach for feature selection and cross-validation. We then compare the results to the performance of four different behavioral models.We found that the behavioral models reached mean accuracies of 90% and above, while the fMRI model only reached 54.84% at the best location in the brain with a spatial distribution similar to the well-known value-tracking network. This low, though significant, accuracy is in line with simulations showing that classifying based on signals with realistic correlations with subjective value produces comparable, low accuracies. These results emphasize the limitations of fMRI recordings from single events to predict human choices, especially when compared to conventional behavioral models. Better performance may be obtained with paradigms that allow the construction of miniblocks to improve the available signal-to-noise ratio.

Download Full-text

Application of Machine Learning Approaches for the Design and Study of Anticancer Drugs

Current Drug Targets ◽

10.2174/1389450119666180809122244 ◽

2019 ◽

Vol 20 (5) ◽

pp. 488-500 ◽

Cited By ~ 6

Author(s):

Yan Hu ◽

Yi Lu ◽

Shuo Wang ◽

Mengying Zhang ◽

Xiaosheng Qu ◽

...

Keyword(s):

Machine Learning ◽

Drug Design ◽

Anticancer Drugs ◽

Nearest Neighbor ◽

Cost Effective ◽

Support Vector ◽

Learning Approaches ◽

K Nearest Neighbor ◽

Activity Prediction ◽

Linear Discriminant

Background: Globally the number of cancer patients and deaths are continuing to increase yearly, and cancer has, therefore, become one of the world's highest causes of morbidity and mortality. In recent years, the study of anticancer drugs has become one of the most popular medical topics. Objective: In this review, in order to study the application of machine learning in predicting anticancer drugs activity, some machine learning approaches such as Linear Discriminant Analysis (LDA), Principal components analysis (PCA), Support Vector Machine (SVM), Random forest (RF), k-Nearest Neighbor (kNN), and Naïve Bayes (NB) were selected, and the examples of their applications in anticancer drugs design are listed. Results: Machine learning contributes a lot to anticancer drugs design and helps researchers by saving time and is cost effective. However, it can only be an assisting tool for drug design. Conclusion: This paper introduces the application of machine learning approaches in anticancer drug design. Many examples of success in identification and prediction in the area of anticancer drugs activity prediction are discussed, and the anticancer drugs research is still in active progress. Moreover, the merits of some web servers related to anticancer drugs are mentioned.

Download Full-text

Machine Learning Methods Applied to the Prediction of Pseudo-nitzschia spp. Blooms in the Galician Rias Baixas (NW Spain)

ISPRS International Journal of Geo-Information ◽

10.3390/ijgi10040199 ◽

2021 ◽

Vol 10 (4) ◽

pp. 199

Author(s):

Francisco M. Bellas Aláez ◽

Jesus M. Torres Palenzuela ◽

Evangelos Spyrakos ◽

Luis González Vilas

Keyword(s):

Machine Learning ◽

Performance Metrics ◽

Prediction Models ◽

Support Vector ◽

False Alarms ◽

Learning Approaches ◽

Learning Methods ◽

Machine Learning Methods ◽

Rías Baixas ◽

New Algorithms

This work presents new prediction models based on recent developments in machine learning methods, such as Random Forest (RF) and AdaBoost, and compares them with more classical approaches, i.e., support vector machines (SVMs) and neural networks (NNs). The models predict Pseudo-nitzschia spp. blooms in the Galician Rias Baixas. This work builds on a previous study by the authors (doi.org/10.1016/j.pocean.2014.03.003) but uses an extended database (from 2002 to 2012) and new algorithms. Our results show that RF and AdaBoost provide better prediction results compared to SVMs and NNs, as they show improved performance metrics and a better balance between sensitivity and specificity. Classical machine learning approaches show higher sensitivities, but at a cost of lower specificity and higher percentages of false alarms (lower precision). These results seem to indicate a greater adaptation of new algorithms (RF and AdaBoost) to unbalanced datasets. Our models could be operationally implemented to establish a short-term prediction system.

Download Full-text

Practical CO2—WAG Field Operational Designs Using Hybrid Numerical-Machine-Learning Approaches

Energies ◽

10.3390/en14041055 ◽

2021 ◽

Vol 14 (4) ◽

pp. 1055

Author(s):

Qian Sun ◽

William Ampomah ◽

Junyu You ◽

Martha Cather ◽

Robert Balch

Keyword(s):

Machine Learning ◽

Oil Recovery ◽

History Matching ◽

Optimization Problems ◽

Learning Technologies ◽

Petroleum Engineering ◽

Support Vector ◽

Learning Approaches ◽

Field Development ◽

Proxy Models

Machine-learning technologies have exhibited robust competences in solving many petroleum engineering problems. The accurate predictivity and fast computational speed enable a large volume of time-consuming engineering processes such as history-matching and field development optimization. The Southwest Regional Partnership on Carbon Sequestration (SWP) project desires rigorous history-matching and multi-objective optimization processes, which fits the superiorities of the machine-learning approaches. Although the machine-learning proxy models are trained and validated before imposing to solve practical problems, the error margin would essentially introduce uncertainties to the results. In this paper, a hybrid numerical machine-learning workflow solving various optimization problems is presented. By coupling the expert machine-learning proxies with a global optimizer, the workflow successfully solves the history-matching and CO2 water alternative gas (WAG) design problem with low computational overheads. The history-matching work considers the heterogeneities of multiphase relative characteristics, and the CO2-WAG injection design takes multiple techno-economic objective functions into accounts. This work trained an expert response surface, a support vector machine, and a multi-layer neural network as proxy models to effectively learn the high-dimensional nonlinear data structure. The proposed workflow suggests revisiting the high-fidelity numerical simulator for validation purposes. The experience gained from this work would provide valuable guiding insights to similar CO2 enhanced oil recovery (EOR) projects.

Download Full-text

Machine Learning Approaches for Prediction of the Compressive Strength of Alkali Activated Termite Mound Soil

Applied Sciences ◽

10.3390/app11114754 ◽

2021 ◽

Vol 11 (11) ◽

pp. 4754

Author(s):

Assia Aboubakar Mahamat ◽

Moussa Mahamat Boukar ◽

Nurudeen Mahmud Ibrahim ◽

Tido Tiwa Stanislas ◽

Numfor Linda Bih ◽

...

Keyword(s):

Compressive Strength ◽

Construction Materials ◽

Curing Temperature ◽

Sustainable Construction ◽

Support Vector ◽

Learning Approaches ◽

Artificial Neural Network Ann ◽

Curing Regime ◽

Alkali Activated

Earth-based materials have shown promise in the development of ecofriendly and sustainable construction materials. However, their unconventional usage in the construction field makes the estimation of their properties difficult and inaccurate. Often, the determination of their properties is conducted based on a conventional materials procedure. Hence, there is inaccuracy in understanding the properties of the unconventional materials. To obtain more accurate properties, a support vector machine (SVM), artificial neural network (ANN) and linear regression (LR) were used to predict the compressive strength of the alkali-activated termite soil. In this study, factors such as activator concentration, Si/Al, initial curing temperature, water absorption, weight and curing regime were used as input parameters due to their significant effect in the compressive strength. The experimental results depict that SVM outperforms ANN and LR in terms of R2 score and root mean square error (RMSE).

Download Full-text

Zonation of Landslide Susceptibility in Ruijin, Jiangxi, China

International Journal of Environmental Research and Public Health ◽

10.3390/ijerph18115906 ◽

2021 ◽

Vol 18 (11) ◽

pp. 5906

Author(s):

Xiaoting Zhou ◽

Weicheng Wu ◽

Ziyu Lin ◽

Guiliang Zhang ◽

Renxiang Chen ◽

...

Keyword(s):

Environmental Factors ◽

Landslide Susceptibility ◽

Urban Areas ◽

Support Vector ◽

Susceptibility Map ◽

Human Society ◽

Learning Approaches ◽

Prevention Measures ◽

Landslide Occurrence ◽

Better Than

Landslides are one of the major geohazards threatening human society. The objective of this study was to conduct a landslide hazard susceptibility assessment for Ruijin, Jiangxi, China, and to provide technical support to the local government for implementing disaster reduction and prevention measures. Machine learning approaches, e.g., random forests (RFs) and support vector machines (SVMs) were employed and multiple geo-environmental factors such as land cover, NDVI, landform, rainfall, lithology, and proximity to faults, roads, and rivers, etc., were utilized to achieve our purposes. For categorical factors, three processing approaches were proposed: simple numerical labeling (SNL), weight assignment (WA)-based and frequency ratio (FR)-based. Then 19 geo-environmental factors were respectively converted into raster to constitute three 19-band datasets, i.e., DS1, DS2, and DS3 from three different processes. Then, 155 observed landslides that occurred in the past decades were vectorized, among which 70% were randomly selected to compose a training set (TS1) and the remaining 30% to form a validation set (VS1). A number of non-landslide (no-risk) samples distributed in the whole study area were identified in low slope (<1–3°) zones such as urban areas and croplands, and also added to the TS1 and VS1 in the same ratio. For comparison, we used the FR approach to identify the no-risk samples in both flat and non-flat areas, and merged them into the field-observed landslides to constitute another pair of training and validation sets (TS2 and VS2) using the same ratio of 7:3. The RF algorithm was applied to model the probability of the landslide occurrence using DS1, DS2, and DS3 as predictive variables and TS1 and TS2 for training to obtain the SNL-based, WA-based, and FR-based RF models, respectively. Verified against VS1 and VS2, the three models have similar overall accuracy (OA) and Kappa coefficient (KC), which are 89.61%, 91.47%, and 94.54%, and 0.7926, 0.8299, and 0.8908, respectively. All of them are much better than the three models obtained by SVM algorithm with OA of 81.79%, 82.86%, and 83%, and KC of 0.6337, 0.655, and 0.660. New case verification with the recent 26 landslide events of 2017–2020 revealed that the landslide susceptibility map from WA-based RF modeling was able to properly identify the high and very high susceptibility zones where 23 new landslides had occurred, and performed better than the SNL-based and FR-based RF modeling, though the latter has a slightly higher OA and KC. Hence, we concluded that all three RF models achieve reasonable risk prediction, but WA-based and FR-based RF modeling deserves a recommendation for application elsewhere. The results of this study may serve as reference for the local authorities in prevention and early warning of landslide hazards.

Download Full-text