scholarly journals EEG data processing with neural network

2019 ◽  
Vol 12 (2) ◽  
pp. 33-36 ◽  
Author(s):  
Tamás Majoros ◽  
Balázs Ujvári ◽  
Stefan Oniga
Keyword(s):  
Neural Network ◽  
High Efficiency ◽  
Brain Activity ◽  
Feedforward Neural Network ◽  
Machine Learning Techniques ◽  
Learning Techniques ◽  
Eeg Data ◽  
Measurement Results ◽  
Eeg Recordings ◽  
Extract Information

Abstract Machine-learning techniques allow to extract information from electroencephalographic (EEG) recordings of brain activity. By processing the measurement results of a publicly available EEG dataset, we were able to obtain information that could be used to train a feedforward neural network to classify two types of volunteer activities with high efficiency.

scholarly journals CNN-based Framework using Spatial Dropping for Enhanced Interpretation of Neural Activity in Motor Imagery Classification

2020 ◽  
Author(s):  
Diego Fabian Collazos Huertas ◽  
Andres Marino Alvarez Meza ◽  
German Castellanos Dominguez
Keyword(s):  
Wavelet Transform ◽  
Motor Imagery ◽  
Continuous Wavelet Transform ◽  
Brain Activity ◽  
Machine Learning Techniques ◽  
Continuous Wavelet ◽  
Brain Response ◽  
Power Spectral ◽  
Learning Techniques ◽  
Eeg Data

Abstract Interpretation of brain activity responses using Motor Imagery (MI) paradigms is vital for medical diagnosis and monitoring. Assessed by machine learning techniques, identification of imagined actions is hindered by substantial intra and inter subject variability. Here, we develop an architecture of Convolutional Neural Networks (CNN) with enhanced interpretation of the spatial brain neural patterns that mainly contribute to the classification of MI tasks. Two methods of 2D-feature extraction from EEG data are contrasted: Power Spectral Density and Continuous Wavelet Transform. For preserving the spatial interpretation of extracting EEG patterns, we project the multi-channel data using a topographic interpolation. Besides, we include a spatial dropping algorithm to remove the learned weights that reflect the localities not engaged with the elicited brain response. Obtained results in a bi-task MI database show that the thresholding strategy in combination with Continuous Wavelet Transform improves the accuracy and enhances the interpretability of CNN architecture, showing that the highest contribution clusters over the sensorimotor cortex with differentiated behavior between μ and β rhythms.

scholarly journals Auto-Colorization of Historical Images Using Deep Convolutional Neural Networks

Mathematics ◽  
2020 ◽  
Vol 8 (12) ◽  
pp. 2258
Author(s):  
Madhab Raj Joshi ◽  
Lewis Nkenyereye ◽  
Gyanendra Prasad Joshi ◽  
S. M. Riazul Islam ◽  
Mohammad Abdullah-Al-Wadud ◽  
...  
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
User Study ◽  
Mean Squared Error ◽  
Color Image ◽  
Machine Learning Techniques ◽  
Global Features ◽  
Black And White ◽  
Historical Images ◽  
Learning Techniques

Enhancement of Cultural Heritage such as historical images is very crucial to safeguard the diversity of cultures. Automated colorization of black and white images has been subject to extensive research through computer vision and machine learning techniques. Our research addresses the problem of generating a plausible colored photograph of ancient, historically black, and white images of Nepal using deep learning techniques without direct human intervention. Motivated by the recent success of deep learning techniques in image processing, a feed-forward, deep Convolutional Neural Network (CNN) in combination with Inception- ResnetV2 is being trained by sets of sample images using back-propagation to recognize the pattern in RGB and grayscale values. The trained neural network is then used to predict two a* and b* chroma channels given grayscale, L channel of test images. CNN vividly colorizes images with the help of the fusion layer accounting for local features as well as global features. Two objective functions, namely, Mean Squared Error (MSE) and Peak Signal-to-Noise Ratio (PSNR), are employed for objective quality assessment between the estimated color image and its ground truth. The model is trained on the dataset created by ourselves with 1.2 K historical images comprised of old and ancient photographs of Nepal, each having 256 × 256 resolution. The loss i.e., MSE, PSNR, and accuracy of the model are found to be 6.08%, 34.65 dB, and 75.23%, respectively. Other than presenting the training results, the public acceptance or subjective validation of the generated images is assessed by means of a user study where the model shows 41.71% of naturalness while evaluating colorization results.

scholarly journals Detection and Severity Evaluation of Combined Rail Defects Using Deep Learning

Vibration ◽  
2021 ◽  
Vol 4 (2) ◽  
pp. 341-356
Author(s):  
Jessada Sresakoolchai ◽  
Sakdirat Kaewunruen
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Deep Learning ◽  
Mean Absolute Error ◽  
Absolute Error ◽  
Machine Learning Techniques ◽  
Rolling Stock ◽  
Raw Data ◽  
Learning Techniques ◽  
Combined Defects

Various techniques have been developed to detect railway defects. One of the popular techniques is machine learning. This unprecedented study applies deep learning, which is a branch of machine learning techniques, to detect and evaluate the severity of rail combined defects. The combined defects in the study are settlement and dipped joint. Features used to detect and evaluate the severity of combined defects are axle box accelerations simulated using a verified rolling stock dynamic behavior simulation called D-Track. A total of 1650 simulations are run to generate numerical data. Deep learning techniques used in the study are deep neural network (DNN), convolutional neural network (CNN), and recurrent neural network (RNN). Simulated data are used in two ways: simplified data and raw data. Simplified data are used to develop the DNN model, while raw data are used to develop the CNN and RNN model. For simplified data, features are extracted from raw data, which are the weight of rolling stock, the speed of rolling stock, and three peak and bottom accelerations from two wheels of rolling stock. In total, there are 14 features used as simplified data for developing the DNN model. For raw data, time-domain accelerations are used directly to develop the CNN and RNN models without processing and data extraction. Hyperparameter tuning is performed to ensure that the performance of each model is optimized. Grid search is used for performing hyperparameter tuning. To detect the combined defects, the study proposes two approaches. The first approach uses one model to detect settlement and dipped joint, and the second approach uses two models to detect settlement and dipped joint separately. The results show that the CNN models of both approaches provide the same accuracy of 99%, so one model is good enough to detect settlement and dipped joint. To evaluate the severity of the combined defects, the study applies classification and regression concepts. Classification is used to evaluate the severity by categorizing defects into light, medium, and severe classes, and regression is used to estimate the size of defects. From the study, the CNN model is suitable for evaluating dipped joint severity with an accuracy of 84% and mean absolute error (MAE) of 1.25 mm, and the RNN model is suitable for evaluating settlement severity with an accuracy of 99% and mean absolute error (MAE) of 1.58 mm.

Borderline and Depression: A Thin EEG Line

2021 ◽  
pp. 155005942110608
Author(s):  
Jakša Vukojević ◽  
Damir Mulc ◽  
Ivana Kinder ◽  
Eda Jovičić ◽  
Krešimir Friganović ◽  
...  
Keyword(s):  
Machine Learning ◽  
Borderline Personality ◽  
Machine Learning Techniques ◽  
Major Depressive ◽  
Everyday Clinical Practice ◽  
Data Set ◽  
Learning Techniques ◽  
Eeg Recordings ◽  
The Given ◽  
Close Interrelationship

In everyday clinical practice, there is an ongoing debate about the nature of major depressive disorder (MDD) in patients with borderline personality disorder (BPD). The underlying research does not give us a clear distinction between those 2 entities, although depression is among the most frequent comorbid diagnosis in borderline personality patients. The notion that depression can be a distinct disorder but also a symptom in other psychopathologies led our team to try and delineate those 2 entities using 146 EEG recordings and machine learning. The utilized algorithms, developed solely for this purpose, could not differentiate those 2 entities, meaning that patients suffering from MDD did not have significantly different EEG in terms of patients diagnosed with MDD and BPD respecting the given data and methods used. By increasing the data set and the spatiotemporal specificity, one could have a more sensitive diagnostic approach when using EEG recordings. To our knowledge, this is the first study that used EEG recordings and advanced machine learning techniques and further confirmed the close interrelationship between those 2 entities.

Autism Spectrum Disorder Identification Using Polynomial Distribution based Convolutional Neural Network

2021 ◽  
Vol 19 (2) ◽  
pp. 19-30
Author(s):  
G. Nagarajan ◽  
Dr.A. Mahabub Basha ◽  
R. Poornima
Keyword(s):  
Neural Network ◽  
Prediction Models ◽  
Autism Spectrum ◽  
Spectrum Disorder ◽  
Machine Learning Techniques ◽  
Hybrid Technique ◽  
Learning Techniques ◽  
Chicken Swarm Optimization ◽  
Sensitivity Specificity ◽  
Polynomial Distribution

One main psychiatric disorder found in humans is ASD (Autistic Spectrum Disorder). The disease manifests in a mental disorder that restricts humans from communications, language, speech in terms of their individual abilities. Even though its cure is complex and literally impossible, its early detection is required for mitigating its intensity. ASD does not have a pre-defined age for affecting humans. A system for effectively predicting ASD based on MLTs (Machine Learning Techniques) is proposed in this work. Hybrid APMs (Autism Prediction Models) combining multiple techniques like RF (Random Forest), CART (Classification and Regression Trees), RF-ID3 (RF-Iterative Dichotomiser 3) perform well, but face issues in memory usage, execution times and inadequate feature selections. Taking these issues into account, this work overcomes these hurdles in this proposed work with a hybrid technique that combines MCSO (Modified Chicken Swarm Optimization) and PDCNN (Polynomial Distribution based Convolution Neural Network) algorithms for its objective. The proposed scheme’s experimental results prove its higher levels of accuracy, precision, sensitivity, specificity, FPRs (False Positive Rates) and lowered time complexity when compared to other methods.

scholarly journals ConvDip: A convolutional neural network for better M/EEG Source Imaging

2020 ◽  
Author(s):  
Lukas Hecker ◽  
Rebekka Rupprecht ◽  
Ludger Tebartz van Elst ◽  
Juergen Kornmeier
Keyword(s):  
Neural Network ◽  
Inverse Problem ◽  
Convolutional Neural Network ◽  
Brain Activity ◽  
Clinical Diagnostics ◽  
Dipole Model ◽  
Source Imaging ◽  
Eeg Source Imaging ◽  
Eeg Data ◽  
Inverse Solutions

AbstractEEG and MEG are well-established non-invasive methods in neuroscientific research and clinical diagnostics. Both methods provide a high temporal but low spatial resolution of brain activity. In order to gain insight about the spatial dynamics of the M/EEG one has to solve the inverse problem, which means that more than one configuration of neural sources can evoke one and the same distribution of EEG activity on the scalp. Artificial neural networks have been previously used successfully to find either one or two dipoles sources. These approaches, however, have never solved the inverse problem in a distributed dipole model with more than two dipole sources. We present ConvDip, a novel convolutional neural network (CNN) architecture that solves the EEG inverse problem in a distributed dipole model based on simulated EEG data. We show that (1) ConvDip learned to produce inverse solutions from a single time point of EEG data and (2) outperforms state-of-the-art methods (eLORETA and LCMV beamforming) on all focused performance measures. (3) It is more flexible when dealing with varying number of sources, produces less ghost sources and misses less real sources than the comparison methods. (4) It produces plausible inverse solutions for real-world EEG recordings and needs less than 40 ms for a single forward pass. Our results qualify ConvDip as an efficient and easy-to-apply novel method for source localization in EEG and MEG data, with high relevance for clinical applications, e.g. in epileptology and real time applications.

scholarly journals Enhancing Classifier Accuracy in Ayurvedic Medicinal Plants using WO-DNN

2019 ◽  
Vol 9 (1) ◽  
pp. 6705-6714
Keyword(s):  
Neural Network ◽  
Medicinal Plants ◽  
Leaf Shape ◽  
Detection Algorithm ◽  
Machine Learning Techniques ◽  
Automatic Identification ◽  
Plant Identification ◽  
Learning Techniques ◽  
Whale Optimization ◽  
Medical Plant

Identification of right medicinal plants that goes in to the formation of a medicine is significant in ayurvedic medicinal industry. This paper focuses around the automatic identification proof of therapeutic plants that are regularly utilized in Ayurveda. The fundamental highlights required to distinguish a medicinal plant is its leaf shape, color and texture. In this paper, we propose efficient accurate classifier for ayurvedic medical plant identification (EAC-AMP) utilizing using hybrid optimal machine learning techniques. In EAC-AMP, image corners detect first and top, bottom leaf edges are computed by the improved edge detection algorithm. After preprocessing, the segmentation can achieve using spider optimization neural network (SONN), which segments leaf regions from an image. The time and frequency domain features are computed by the symbolic accurate approximation (SAX); other features shape features, color features and tooth features are computed by the two-dimensional binary phase encoding (2DBPE). Finally, a whale optimization with deep neural network (DNN) classifier is used to characterize the type of plants. Accuracy in identification of any ayurvedic plant leaf is achieved by understanding and extracting the plant features. The main objective of the proposed EAC-AMP approach is to increase the accuracy of classifier. MATLAB experimental analysis showed better results such as accuracy, sensitivity and specificity.

scholarly journals Signal-space projection suppresses the tACS artifact in EEG recordings

2019 ◽  
Author(s):  
Johannes Vosskuhl ◽  
Tuomas P. Mutanen ◽  
Toralf Neuling ◽  
Risto J. Ilmoniemi ◽  
Christoph S. Herrmann
Keyword(s):  
Brain Activity ◽  
Current Source ◽  
Oscillatory Activity ◽  
Signal Space ◽  
Artifact Correction ◽  
Eeg Data ◽  
Before And After ◽  
Transcranial Alternating Current Stimulation ◽  
Space Projection ◽  
Eeg Recordings

1.AbstractBackgroundTo probe the functional role of brain oscillations, transcranial alternating current stimulation (tACS) has proven to be a useful neuroscientific tool. Because of the huge tACS-caused artifact in electroencephalography (EEG) signals, tACS–EEG studies have been mostly limited to compare brain activity between recordings before and after concurrent tACS. Critically, attempts to suppress the artifact in the data cannot assure that the entire artifact is removed while brain activity is preserved. The current study aims to evaluate the feasibility of specific artifact correction techniques to clean tACS-contaminated EEG data.New MethodIn the first experiment, we used a phantom head to have full control over the signal to be analyzed. Driving pre-recorded human brain-oscillation signals through a dipolar current source within the phantom, we simultaneously applied tACS and compared the performance of different artifact-correction techniques: sine subtraction, template subtraction, and signal-space projection (SSP). In the second experiment, we combined tACS and EEG on a human subject to validate the best-performing data-correction approach.ResultsThe tACS artifact was highly attenuated by SSP in the phantom and the human EEG; thus, we were able to recover the amplitude and phase of the oscillatory activity. In the human experiment, event-related desynchronization could be restored after correcting the artifact.Comparison with existing methodsThe best results were achieved with SSP, which outperformed sine subtraction and template subtraction.ConclusionsOur results demonstrate the feasibility of SSP by applying it to human tACS–EEG data.

scholarly journals Estimating Forest Carbon Fluxes Using Machine Learning Techniques Based on Eddy Covariance Measurements

2018 ◽  
Vol 10 (1) ◽  
pp. 203 ◽  
Author(s):  
Xianming Dou ◽  
Yongguo Yang ◽  
Jinhui Luo
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Eddy Covariance ◽  
Carbon Flux ◽  
Carbon Fluxes ◽  
Forest Carbon ◽  
Machine Learning Techniques ◽  
Support Vector ◽  
Inference System ◽  
Learning Techniques

Approximating the complex nonlinear relationships that dominate the exchange of carbon dioxide fluxes between the biosphere and atmosphere is fundamentally important for addressing the issue of climate change. The progress of machine learning techniques has offered a number of useful tools for the scientific community aiming to gain new insights into the temporal and spatial variation of different carbon fluxes in terrestrial ecosystems. In this study, adaptive neuro-fuzzy inference system (ANFIS) and generalized regression neural network (GRNN) models were developed to predict the daily carbon fluxes in three boreal forest ecosystems based on eddy covariance (EC) measurements. Moreover, a comparison was made between the modeled values derived from these models and those of traditional artificial neural network (ANN) and support vector machine (SVM) models. These models were also compared with multiple linear regression (MLR). Several statistical indicators, including coefficient of determination (R2), Nash-Sutcliffe efficiency (NSE), bias error (Bias) and root mean square error (RMSE) were utilized to evaluate the performance of the applied models. The results showed that the developed machine learning models were able to account for the most variance in the carbon fluxes at both daily and hourly time scales in the three stands and they consistently and substantially outperformed the MLR model for both daily and hourly carbon flux estimates. It was demonstrated that the ANFIS and ANN models provided similar estimates in the testing period with an approximate value of R2 = 0.93, NSE = 0.91, Bias = 0.11 g C m−2 day−1 and RMSE = 1.04 g C m−2 day−1 for daily gross primary productivity, 0.94, 0.82, 0.24 g C m−2 day−1 and 0.72 g C m−2 day−1 for daily ecosystem respiration, and 0.79, 0.75, 0.14 g C m−2 day−1 and 0.89 g C m−2 day−1 for daily net ecosystem exchange, and slightly outperformed the GRNN and SVM models. In practical terms, however, the newly developed models (ANFIS and GRNN) are more robust and flexible, and have less parameters needed for selection and optimization in comparison with traditional ANN and SVM models. Consequently, they can be used as valuable tools to estimate forest carbon fluxes and fill the missing carbon flux data during the long-term EC measurements.

Sign in / Sign up

Export Citation Format

Share Document