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 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 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

Novel Low-Pass Microwave Filter Based on Rectangular Ring DGS

2013 ◽  
Vol 273 ◽  
pp. 371-374
Author(s):  
Bao Ping Li ◽  
Yan Liang Zhang
Keyword(s):  
Stop Band ◽  
Center Frequency ◽  
Pass Band ◽  
Band Pass Filter ◽  
Defected Ground Structure ◽  
Ground Structure ◽  
Pass Filter ◽  
Low Pass Filter ◽  
Compact Size ◽  
Low Pass

Due to the frequency response periodicity of distributed transmission line, microstrip band-pass filter usually produces parasitic pass-band and outputs harmonics away from the center frequency of main pass-band. Based on the study of rectangular ring defected ground structure, a 5-order microstrip LPF(low-pass filter) was designed using the single-pole band-stop and slow-wave characteristics of the rectangular ring DGS(Defected Ground Structure) and SISS(Step-Impedance Shunt Stub) structure. Compared with traditional LPF, this LPF presents the advantages of compact size, low insertion loss, broad stop-band and high steep. It also validates the requirements of miniaturization and high performance for filters.

scholarly journals Design and Development of Filtering Antenna for S-Band Applications with High out-of-band Rejection

2019 ◽  
Vol 9 (1S) ◽  
pp. 180-187
Keyword(s):  
Antenna Array ◽  
Patch Antenna ◽  
Equivalent Circuit Model ◽  
Design Procedure ◽  
Pass Band ◽  
Band Pass Filter ◽  
Coupled Resonators ◽  
Pass Filter ◽  
Antenna Structure ◽  
Band Pass

In this paper, the design, simulation and fabrication of a filtering antenna is proposed. The filtering antenna structure is, therefore, framed by integrating elements, such as the feed line, parallel coupled resonators and the microstrip patch antenna array. The combined elements are designed for third order Chebyshev band pass filter with a pass band ripple of 0.1 dB and the integrated structure is more suitable for different S-band (2 GHz – 4 GHz) wireless applications. The equivalent circuit model for the proposed filtering antenna structure is analysed and the design procedure of the filter is also presented in detail. The 1x2 rectangular patch antenna array acts both as a radiating element and also as the last resonator of the band pass filter. The proposed filtering antenna structure results in high out-of-band rejection, enhanced bandwidth and a gain of about 209 MHz and 1.53 dB. The fabricated result agrees well with the simulation characteristics

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.

scholarly journals Design of UWB Filter with WLAN Notch

2012 ◽  
Vol 2012 ◽  
pp. 1-4 ◽  
Author(s):  
Harish Kumar ◽  
MD. Upadhayay
Keyword(s):  
Circuit Simulation ◽  
Ground Plane ◽  
Stop Band ◽  
Simulation Software ◽  
Pass Band ◽  
Area Network ◽  
Band Pass Filter ◽  
Frequency Range ◽  
Pass Filter ◽  
Band Pass

UWB technology- (operating in broad frequency range of 3.1–10.6 GHz) based filter with WLAN notch has shown great achievement for high-speed wireless communications. To satisfy the UWB system requirements, a band pass filter with a broad pass band width, low insertion loss, and high stop-band suppression are needed. UWB filter with wireless local area network (WLAN) notch at 5.6 GHz and 3 dB fractional bandwidth of 109.5% using a microstrip structure is presented. Initially a two-transmission-pole UWB band pass filter in the frequency range 3.1–10.6 GHz is achieved by designing a parallel-coupled microstrip line with defective ground plane structure using GML 1000 substrate with specifications: dielectric constant 3.2 and thickness 0.762 mm at centre frequency 6.85 GHz. In this structure aλ/4 open-circuited stub is introduced to achieve the notch at 5.6 GHz to avoid the interference with WLAN frequency which lies in the desired UWB band. The design structure was simulated on electromagnetic circuit simulation software and fabricated by microwave integrated circuit technique. The measured VNA results show the close agreement with simulated results.

Gm-C Complex Band-Pass Filter with Tuning Circuit in 0.18μm CMOS

2012 ◽  
Vol 229-231 ◽  
pp. 1605-1608
Author(s):  
Xiang Ning Fan ◽  
Kuan Bao ◽  
Rui Wu ◽  
Jun Bo Liu
Keyword(s):  
Supply Voltage ◽  
Pass Band ◽  
Band Pass Filter ◽  
Voltage Measurement ◽  
Pass Filter ◽  
Measurement Results ◽  
Band Pass ◽  
Tuning Circuit ◽  
C Complex ◽  
Image Rejection Ratio

This paper presents a 0.18μm CMOS based Gm-C complex band-pass (CBP) filter with tuning circuit. Active-Gm-C structure with Nauta transconductor and phase-locked loop (PLL) architecture are adopted by the filter and the tuning circuit respectively which can achieve accurate frequency response. The layout size is 970μm×920μm. Under a 1.8V supply voltage, measurement results show that the pass-band gain and the ripple of the filter is 3.1dB and 3dB respectively. The bandwidth after tuning is 32.5MHz, image rejection ratio (IRR) is about 47dB, and the power dissipation of the filter is about 21.6mW.

scholarly journals Power Transformer Partial Discharge Fault Diagnosis Based on Multidimensional Feature Region

2016 ◽  
Vol 2016 ◽  
pp. 1-11 ◽  
Author(s):  
Rong Jia ◽  
Yongtao Xie ◽  
Hua Wu ◽  
Jian Dang ◽  
Kaisong Dong
Keyword(s):  
Frequency Band ◽  
Power Transformer ◽  
Partial Discharge ◽  
Extraction Methods ◽  
Sample Entropy ◽  
Support Vector ◽  
Band Pass Filter ◽  
Pass Filter ◽  
Hilbert Huang Transform ◽  
Frequency Band Energy

Effectively extracting power transformer partial discharge (PD) signals feature is of great significance for monitoring power transformer insulation condition. However, there has been lack of practical and effective extraction methods. For this reason, this paper suggests a novel method for the PD signal feature extraction based on multidimensional feature region. Firstly, in order to better describe differences in each frequency band of fault signals, empirical mode decomposition (EMD) and Hilbert-Huang transform (HHT) band-pass filter wave for raw signal is carried out. And the component of raw signals on each frequency band can be obtained. Secondly, the sample entropy value and the energy value of each frequency band component are calculated. Using the difference of each frequency band energy and complexity, signals feature region is established by the multidimensional energy parameters and the multidimensional sample entropy parameters to describe PD signals multidimensional feature information. Finally, partial discharge faults are classified by sphere-structured support vector machines algorithm. The result indicates that this method is able to identify and classify different partial discharge faults.

Study on Infrared Transparent Radar Double Band-Pass Filter

2011 ◽  
Vol 328-330 ◽  
pp. 1503-1506
Author(s):  
Hong Yan Jia ◽  
Xiao Guo Feng
Keyword(s):  
Electromagnetic Waves ◽  
Frequency Selective Surface ◽  
Shielding Effect ◽  
Pass Band ◽  
Band Pass Filter ◽  
Double Pass ◽  
Pass Filter ◽  
Resonance Frequencies ◽  
New Thinking ◽  
Band Pass

To realize the functions of infrared transparent as well as radar double– pass Band, A Y loop and Y slot compound element Frequency Selective Surface (FSS) structure is proposed, which takes an infrared transparent inductive mesh as a substrate. The proposed structure is analyzed based on Galerkin spectral method. The transitivity of infrared (3um-5um) as well as the radar double passed band with two resonance frequencies (31GHz and 54GHz) is discussed. The result reveals that this structure has function of infrared transparent as well as stable radar double–band filter with effective shielding effect on S-band and C-band radar electromagnetic waves. The design with multiple passband is suitable for radar/IR composite guidance and it also offers a kind of new thinking way of design for multi-mode compound guidance systems.

scholarly journals Automatic Diagnosis of Epileptic Seizures in EEG Signals Using Fractal Dimension Features and Convolutional Autoencoder Method

2021 ◽  
Vol 5 (4) ◽  
pp. 78
Author(s):  
Anis Malekzadeh ◽  
Assef Zare ◽  
Mahdi Yaghoobi ◽  
Roohallah Alizadehsani
Keyword(s):  
Fractal Dimension ◽  
Support Vector ◽  
Fluctuation Analysis ◽  
Band Pass Filter ◽  
Classification Problems ◽  
Complex Wavelet Transform ◽  
Eeg Signals ◽  
Pass Filter ◽  
Box Counting ◽  
Convolutional Autoencoder

This paper proposes a new method for epileptic seizure detection in electroencephalography (EEG) signals using nonlinear features based on fractal dimension (FD) and a deep learning (DL) model. Firstly, Bonn and Freiburg datasets were used to perform experiments. The Bonn dataset consists of binary and multi-class classification problems, and the Freiburg dataset consists of two-class EEG classification problems. In the preprocessing step, all datasets were prepossessed using a Butterworth band pass filter with 0.5–60 Hz cut-off frequency. Then, the EEG signals of the datasets were segmented into different time windows. In this section, dual-tree complex wavelet transform (DT-CWT) was used to decompose the EEG signals into the different sub-bands. In the following section, in order to feature extraction, various FD techniques were used, including Higuchi (HFD), Katz (KFD), Petrosian (PFD), Hurst exponent (HE), detrended fluctuation analysis (DFA), Sevcik, box counting (BC), multiresolution box-counting (MBC), Margaos-Sun (MSFD), multifractal DFA (MF-DFA), and recurrence quantification analysis (RQA). In the next step, the minimum redundancy maximum relevance (mRMR) technique was used for feature selection. Finally, the k-nearest neighbors (KNN), support vector machine (SVM), and convolutional autoencoder (CNN-AE) were used for the classification step. In the classification step, the K-fold cross-validation with k = 10 was employed to demonstrate the effectiveness of the classifier methods. The experiment results show that the proposed CNN-AE method achieved an accuracy of 99.736% and 99.176% for the Bonn and Freiburg datasets, respectively.

Sign in / Sign up

Export Citation Format

Share Document