scholarly journals Multiclass classification of motor imagery EEG signals using ensemble classifiers & cross-correlation

2018 ◽  
Vol 7 (2.6) ◽  
pp. 163
Author(s):  
D Hari Krishna ◽  
I A.Pasha ◽  
T Satya Savithri
Keyword(s):  
Cross Correlation ◽  
Signal To Noise Ratio ◽  
Majority Voting ◽  
Support Vector ◽  
Band Pass Filter ◽  
Eeg Signal ◽  
Ensemble Classifiers ◽  
K Nearest Neighbors ◽  
Pass Filter ◽  
Linear Discriminant

To communicate without any muscle movement and purely based on brain signal has been the goal of Brain computer interfacing (BCI). Recent BCI based studies reported more and more accurate detection of brain states. This paper proposes a study that detects EEG signal belonging todifferent imaginary motor activities (Right leg, right hand, left leg and left hand). The Electroencephalogram (EEG) signal has been conditioned by band pass filter (BPF) to improve signal to noise ratio (SNR). The proposed method is based on similarity between signals to extract features. For measuring the similarity between signals, Cross correlation (CC) is used. An ensemble set of five classifiers (Linear Discriminant Analysis (LDA), K-Nearest Neighbors (KNN), Support Vector Machine (SVM), Naïve Bayes (NB) and Binary Decision Tree) was used collectively.  As the similarity measurement was binary in nature, one versus rest (OVR) approach was used for multi class classification. Random subset of features was used to train the ensemble of classifiers. The classification label was obtained by using majority voting. An average accuracy of 89.57% was observed among all 10 subjects.

scholarly journals Ensemble Voting-Based Multichannel EEG Classification in a Subject-Independent P300 Speller

2021 ◽  
Vol 11 (23) ◽  
pp. 11252
Author(s):  
Ayana Mussabayeva ◽  
Prashant Kumar Jamwal ◽  
Muhammad Tahir Akhtar
Keyword(s):  
Healthy Subjects ◽  
Single Channel ◽  
Event Related Potentials ◽  
Support Vector ◽  
Ensemble Classifiers ◽  
K Nearest Neighbors ◽  
Linear Discriminant ◽  
P300 Speller ◽  
Related Potentials ◽  
Als Patients

Classification of brain signal features is a crucial process for any brain–computer interface (BCI) device, including speller systems. The positive P300 component of visual event-related potentials (ERPs) used in BCI spellers has individual variations of amplitude and latency that further changse with brain abnormalities such as amyotrophic lateral sclerosis (ALS). This leads to the necessity for the users to train the speller themselves, which is a very time-consuming procedure. To achieve subject-independence in a P300 speller, ensemble classifiers are proposed based on classical machine learning models, such as the support vector machine (SVM), linear discriminant analysis (LDA), k-nearest neighbors (kNN), and the convolutional neural network (CNN). The proposed voters were trained on healthy subjects’ data using a generic training approach. Different combinations of electroencephalography (EEG) channels were used for the experiments presented, resulting in single-channel, four-channel, and eight-channel classification. ALS patients’ data represented robust results, achieving more than 90% accuracy when using an ensemble of LDA, kNN, and SVM on four active EEG channels data in the occipital area of the brain. The results provided by the proposed ensemble voting models were on average about 5% more accurate than the results provided by the standalone classifiers. The proposed ensemble models could also outperform boosting algorithms in terms of computational complexity or accuracy. The proposed methodology shows the ability to be subject-independent, which means that the system trained on healthy subjects can be efficiently used for ALS patients. Applying this methodology for online speller systems removes the necessity to retrain the P300 speller.

Sensory motor imagery EEG classification based on non-dyadic wavelets using dynamic weighted majority ensemble classification

2021 ◽  
Vol 15 (1) ◽  
pp. 33-43
Author(s):  
Poonam Chaudhary ◽  
Rashmi Agrawal
Keyword(s):  
Motor Imagery ◽  
Ensemble Classification ◽  
Support Vector ◽  
Pass Band ◽  
Band Pass Filter ◽  
Eeg Signal ◽  
Pass Filter ◽  
Frequency Bands ◽  
Sensory Motor ◽  
Bci System

The classification accuracy has become a significant challenge and an important task in sensory motor imagery (SMI) electroencephalogram (EEG) based Brain Computer interface (BCI) system. This paper compares ensemble classification framework with individual classifiers. The main objective is to reduce the inference of non-stationary and transient information and improves the classification decision in BCI system. The framework comprises the three phases as follows: (1) the EEG signal first decomposes into triadic frequency bands: low pass band, band pass filter and high pass filter to localize α, β and high γ frequency bands within the EEG signals, (2) Then, Common spatial pattern (CSP) algorithm has been applied on the extracted frequencies in phase I to heave out the important features of EEG signal, (3) Further, an existing Dynamic Weighted Majiority (DWM) ensemble classification algorithm has been implemented using features extracted in phase II, for final class label decision. J48, Naive Bayes, Support Vector Machine, and K-Nearest Neighbor classifiers used as base classifiers for making a diverse ensemble of classifiers. A comparative study between individual classifiers and ensemble framework has been included in the paper. Experimental evaluation and assessment of the performance of the proposed model is done on the publically available datasets: BCI Competition IV dataset IIa and BCI Competition III dataset IVa. The ensemble based learning method gave the highest accuracy among all. The average sensitivity, specificity, and accuracy of 85.4%, 86.5%, and 85.6% were achieved with a kappa value of 0.59 using DWM classification.

scholarly journals An Automatic Classification Method of Sleep Apnea Events Based on EEG Frequency Sub-band Division

2021 ◽  
Author(s):  
Yao Wang ◽  
Xiaohong Wang ◽  
Weiming Li ◽  
Siyu Ji ◽  
Tianshun Yang ◽  
...  
Keyword(s):  
Sleep Apnea ◽  
Random Forest ◽  
Classification Performance ◽  
Infinite Impulse Response ◽  
Band Pass Filter ◽  
Eeg Signal ◽  
K Nearest Neighbors ◽  
Pass Filter ◽  
Feature Extraction Method ◽  
Welch Method

Abstract Sleep apnea is a kind of sleep disorder with a high prevalence rate. It is manifested as the abnormal stop of breathing during sleep and is highly dangerous to human health. The purpose of this research is to find a simple, and effective feature extraction method that can able to distinguish obstructive apnea events, central apnea events, and normal breathing events. Unlike conventional methods, the method illustrated in this study used the Infinite Impulse Response Butterworth Band pass filter to divide the Electroencephalogram (EEG) signal into 5, 7, 9 or 11 frequency sub-bands and then used the Welch method to extract the power features of these frequency sub-band signals, which were subsequently used as classifier input. Random forest, K-nearest neighbors and bagging classifiers were investigated. The results showed that in several different frequency sub-band division methods of EEG signals, the features extracted from the EEG signal that was divided into 11 frequency sub-bands were more conducive to the classification of sleep apnea events. The random forest classifier achieved the highest average accuracy, macro F1 and kappa coefficient in three types of events, which were 90.43%, 90.38% and 0.88, respectively. Compared with existing methods, the method used in the present study has higher classification performance.

Identification of Brain disorders by Sub-band Decomposition of EEG signals and Measurement of Signal to Noise Ratio

2016 ◽  
Vol 4 (3) ◽  
pp. 568
Author(s):  
Hadaate Ullah ◽  
Shahin Mahmud ◽  
Rubana Hoque Chowdhury
Keyword(s):  
Feature Extraction ◽  
Signal To Noise Ratio ◽  
Automated System ◽  
Discrete Wavelet ◽  
Band Pass Filter ◽  
Eeg Signal ◽  
Brain Disorders ◽  
Signal To Noise ◽  
Pass Filter ◽  
Noise Ratio

<p>In the case of medical science, one of the most restless researches is the identification of abnormalities in brain. Electroencephalogram (EEG) is the main tool for determining the electrical activity of brain and it contains rich information associated to the varieties physiological states of brain. The purpose of this task is to identify the EEG signal as order or disorder. It is proposed to enrich an automated system for the identification of brain disorders. An EEG signal of a patient has been taken as a sample. The simulation has been done by MATLAB. The file which consists of the signal has been called in and plotted the signals in MATLAB. The proposed system covers pre-processing, feature extraction, feature selection and classification. By the pre-processing the noises are ejected. In this case the signal has been filtered using band pass filter. The Discrete Wavelet Transform (DWT) has been used to decompose the EEG signal into Sub-band signal. The feature extraction methods have been used to extract the EEG signal into frequency domain and the time domain features. The SNR (Signal to Noise ratio) is obtained in this work is 1.1281dB.<strong></strong></p>

scholarly journals Improving Motor Imagery EEG Signals Classification Accuracy with CSP by Available Machine Learning Approach

2021 ◽  
Vol 12 (2) ◽  
pp. 67-77
Author(s):  
Umme Farhana ◽  
Mst Jannatul Ferdous
Keyword(s):  
Machine Learning ◽  
Feature Extraction ◽  
Motor Imagery ◽  
Classification Accuracy ◽  
Support Vector ◽  
Band Pass Filter ◽  
K Nearest Neighbor ◽  
Eeg Signals ◽  
Pass Filter ◽  
Linear Discriminant

In brain computer interface (BCI) systems, the electroencephalography (EEG) signals give a pathway to a motor disabled person to communicate outside using the brain signal and a computer. EEG signals of different motor imagery (MI) movements can be differentiated using an effective classification technique to aid a motor disabled patient. The purpose of this paper is to classify two different types of MI movement tasks, movement of the left hand and movement of the right foot EEG signals accurately. For this purpose we have used a publicly available dataset. Since the feature extraction for classification is an important task, so we have used popular common spatial pattern (CSP) method for spatial feature extraction. Two different machine learning classifiers named support vector machine (SVM) and K-nearest neighbor (KNN) have been used to verify the proposed method. We got the highest average results 95.55%, 98.73% and 92.38% in case of SVM and 93.5%, 98.73% and 90.15% in case of KNN for classification accuracy, sensitivity, and specificity, respectively when a Butterworth band-pass filter passed through [10–30] Hz. On the other hand accuracy came to 89.4% in [10-30] Hz when applying CSP for feature extraction and fisher linear discriminant analysis (FLDA) for classification on this dataset earlier. Journal of Engineering Science 12(2), 2021, 67-77

scholarly journals Performance of channel selection used for Multi-class EEG signal classification of motor imagery

2019 ◽  
Vol 15 (3) ◽  
pp. 1305
Author(s):  
Djelloul Kheira ◽  
M. Beladgham
Keyword(s):  
Support Vector ◽  
Eeg Signal ◽  
K Nearest Neighbors ◽  
Linear Discriminant ◽  
Left Hand ◽  
Time Frequency ◽  
Non Invasive ◽  
Average Accuracy ◽  
Motor Activities

<p>In this paper, a study of a non-invasive brain-machine interfaces for the classification of 4 imaginary are presented. Performance comparisons using time-frequency analysis between the Linear Discriminant Analysis motor activities (left hand, right hand, foot, tongue) with the BCI competition III dataset IIIa is (LDA), the Support Vector Machine (SVM) and the K-Nearest Neighbors (KNN) algorithms have been carried. The number and position of electrodes for each subject were investigated to provide an improvement for the classification accuracy of the algorithm. Results show that the electrode positions varied from subject to subject; moreover , using one subset of the channels enhanced the classification performances compared to literature data. an average accuracy of 86.06% was observed among all 3 subjects.<strong></strong></p>

scholarly journals Artifacts removal from breath sound recordings in pediatric population

2018 ◽  
Vol 154 ◽  
pp. 01046
Author(s):  
Yusuf A Amrulloh ◽  
Jawahir A K Haq
Keyword(s):  
Signal To Noise Ratio ◽  
Pediatric Population ◽  
Breath Sound ◽  
Discrete Wavelet ◽  
Band Pass Filter ◽  
Pass Filter ◽  
Sound Recordings ◽  
Breath Sounds ◽  
Band Pass ◽  
Lower Magnitude

Breath sound recordings from pediatric subjects pose more processing complications. Children, especially the younger ones, are not able to follow instructions to stay calm during recording. This makes their recordings not only contain stationary artifacts but also non-stationary artifacts such as movement of subjects and their heartbeats. Further, the breath sounds from pediatric subjects also have lower magnitude compared to adults. In this work, we proposed to address those problems by developing a method to remove the artifacts from breath sound recordings. We implemented a combination of a Butterworth band pass filter and a discrete wavelet filter. We tested three types of wavelets (Coiflet, Symlet and Daubechies). Ten level decompositions and a set of hard thresholds were implemented in our work. Our results show that our developed method was capable of removing the artifacts significantly while maintaining the signal of interest. The highest signal to noise ratio improvement (10.65dB) was achieved by 32 orders Symlet.

scholarly journals Detection of 2D and 3D Video Transitions Based on EEG Power

2020 ◽  
Author(s):  
Negin Manshouri ◽  
Mesut Melek ◽  
Temel Kayikcioglu
Keyword(s):  
Steady State ◽  
Support Vector ◽  
Success Rates ◽  
K Nearest Neighbors ◽  
3D Vision ◽  
Linear Discriminant ◽  
Parietal Lobes ◽  
Brain Signals ◽  
Sudden Transition ◽  
2D And 3D

Despite the long and extensive history of 3D technology, it has recently attracted the attention of researchers. This technology has become the center of interest of young people because of the real feelings and sensations it creates. People see their environment as 3D because of their eye structure. In this study, it is hypothesized that people lose their perception of depth during sleepy moments and that there is a sudden transition from 3D vision to 2D vision. Regarding these transitions, the EEG signal analysis method was used for deep and comprehensive analysis of 2D and 3D brain signals. In this study, a single-stream anaglyph video of random 2D and 3D segments was prepared. After watching this single video, the obtained EEG recordings were considered for two different analyses: the part involving the critical transition (transition-state) and the state analysis of only the 2D versus 3D or 3D versus 2D parts (steady-state). The main objective of this study is to see the behavioral changes of brain signals in 2D and 3D transitions. To clarify the impacts of the human brain&rsquo;s power spectral density (PSD) in 2D-to-3D (2D_3D) and 3D-to-2D (3D_2D) transitions of anaglyph video, 9 visual healthy individuals were prepared for testing in this pioneering study. Spectrogram graphs based on Short Time Fourier transform (STFT) were considered to evaluate the power spectrum analysis in each EEG channel of transition or steady-state. Thus, in 2D and 3D transition scenarios, important channels representing EEG frequency bands and brain lobes will be identified. To classify the 2D and 3D transitions, the dominant bands and time intervals representing the maximum difference of PSD were selected. Afterward, effective features were selected by applying statistical methods such as standard deviation (SD), maximum (max), and Hjorth parameters to epochs indicating transition intervals. Ultimately, k-Nearest Neighbors (k-NN), Support Vector Machine (SVM), and Linear Discriminant Analysis (LDA) algorithms were applied to classify 2D_3D and 3D_2D transitions. The frontal, temporal, and partially parietal lobes show 2D_3D and 3D_2D transitions with a good classification success rate. Overall, it was found that Hjorth parameters and LDA algorithms have 71.11% and 77.78% classification success rates for transition and steady-state, respectively.

scholarly journals Identification of optimum segment in single channel EEG biometric system

2021 ◽  
Vol 23 (3) ◽  
pp. 1847
Author(s):  
Muhammad Afif Hendrawan ◽  
Pramana Yoga Saputra ◽  
Cahya Rahmad
Keyword(s):  
Single Channel ◽  
Support Vector ◽  
Discrete Wavelet ◽  
Eeg Signal ◽  
Alpha Band ◽  
Biometric System ◽  
Linear Discriminant ◽  
Power Spectral ◽  
Eyes Open ◽  
High Level

Nowadays, biometric modalities have gained popularity in security systems. Nevertheless, the conventional commercial-grade biometric system addresses some issues. The biggest problem is that they can be imposed by artificial biometrics. The electroencephalogram (EEG) is a possible solution. It is nearly impossible to replicate because it is dependent on human mental activity. Several studies have already demonstrated a high level of accuracy. However, it requires a large number of sensors and time to collect the signal. This study proposed a biometric system using single-channel EEG recorded during resting eyes open (EO) conditions. A total of 45 EEG signals from 9 subjects were collected. The EEG signal was segmented into 5 second lengths. The alpha band was used in this study. Discrete wavelet transform (DWT) with Daubechies type 4 (db4) was employed to extract the alpha band. Power spectral density (PSD) was extracted from each segment as the main feature. Linear discriminant analysis (LDA) and support vector machine (SVM) were used to classify the EEG signal. The proposed method achieved 86% accuracy using LDA only from the third segment. Therefore, this study showed that it is possible to utilize single-channel EEG during a resting EO state in a biometric system.

scholarly journals Comparing Performances of CNN, BP, and SVM Algorithms for Differentiating Sweet Pepper Parts for Harvest Automation

2021 ◽  
Vol 11 (20) ◽  
pp. 9583
Author(s):  
Bongki Lee ◽  
Donghwan Kam ◽  
Yongjin Cho ◽  
Dae-Cheol Kim ◽  
Dong-Hoon Lee
Keyword(s):  
Success Rate ◽  
Sweet Pepper ◽  
Local Features ◽  
Bp Algorithm ◽  
Support Vector ◽  
Band Pass Filter ◽  
Pass Filter ◽  
Plant Parts ◽  
Speeded Up Robust Features ◽  
Recognition Success

For harvest automation of sweet pepper, image recognition algorithms for differentiating each part of a sweet pepper plant were developed and performances of these algorithms were compared. An imaging system consisting of two cameras and six halogen lamps was built for sweet pepper image acquisition. For image analysis using the normalized difference vegetation index (NDVI), a band-pass filter in the range of 435 to 950 nm with a broad spectrum from visible light to infrared was used. K-means clustering and morphological skeletonization were used to classify sweet pepper parts to which the NDVI was applied. Scale-invariant feature transform (SIFT) and speeded-up robust features (SURFs) were used to figure out local features. Classification performances of a support vector machine (SVM) using the radial basis function kernel and backpropagation (BP) algorithm were compared to classify local SURFs of fruits, nodes, leaves, and suckers. Accuracies of the BP algorithm and the SVM for classifying local features were 95.96 and 63.75%, respectively. When the BP algorithm was used for classification of plant parts, the recognition success rate was 94.44% for fruits, 84.73% for nodes, 69.97% for leaves, and 84.34% for suckers. When CNN was used for classifying plant parts, the recognition success rate was 99.50% for fruits, 87.75% for nodes, 90.50% for leaves, and 87.25% for suckers.

Sign in / Sign up

Export Citation Format

Share Document