Artif Intell Med - Channel selection and classification of electroencephalogram signals: an artificial neural network and genetic algorithm-based approach.

Tópicos

{ featur(3375) classif(2383) classifi(1994) }
{ signal(2180) analysi(812) frequenc(800) }
{ first(2504) two(1366) second(1323) }
{ network(2748) neural(1063) input(814) }
{ analysi(2126) use(1163) compon(1037) }
{ imag(1057) registr(996) error(939) }
{ data(3963) clinic(1234) research(1004) }
{ learn(2355) train(1041) set(1003) }
{ can(774) often(719) complex(702) }
{ error(1145) method(1030) estim(1020) }
{ estim(2440) model(1874) function(577) }
{ control(1307) perform(991) simul(935) }
{ case(1353) use(1143) diagnosi(1136) }
{ sampl(1606) size(1419) use(1276) }
{ implement(1333) system(1263) develop(1122) }
{ system(1976) rule(880) can(841) }
{ problem(2511) optim(1539) algorithm(950) }
{ method(984) reconstruct(947) comput(926) }
{ model(2656) set(1616) predict(1553) }
{ studi(2440) review(1878) systemat(933) }
{ blood(1257) pressur(1144) flow(957) }
{ gene(2352) biolog(1181) express(1162) }
{ can(981) present(881) function(850) }
{ model(3404) distribut(989) bayesian(671) }
{ algorithm(1844) comput(1787) effici(935) }
{ method(1557) propos(1049) approach(1037) }
{ studi(1410) differ(1259) use(1210) }
{ model(2341) predict(2261) use(1141) }
{ studi(1119) effect(1106) posit(819) }
{ state(1844) use(1261) util(961) }
{ medic(1828) order(1363) alert(1069) }
{ use(976) code(926) identifi(902) }
{ research(1085) discuss(1038) issu(1018) }
{ research(1218) medic(880) student(794) }
{ health(1844) social(1437) communiti(874) }
{ data(1737) use(1416) pattern(1282) }
{ method(1219) similar(1157) match(930) }
{ imag(2675) segment(2577) method(1081) }
{ clinic(1479) use(1117) guidelin(835) }
{ design(1359) user(1324) use(1319) }
{ model(2220) cell(1177) simul(1124) }
{ general(901) number(790) one(736) }
{ search(2224) databas(1162) retriev(909) }
{ howev(809) still(633) remain(590) }
{ model(3480) simul(1196) paramet(876) }
{ cost(1906) reduc(1198) effect(832) }
{ group(2977) signific(1463) compar(1072) }
{ patient(1821) servic(1111) care(1106) }
{ use(2086) technolog(871) perceiv(783) }
{ survey(1388) particip(1329) question(1065) }
{ detect(2391) sensit(1101) algorithm(908) }
{ imag(1947) propos(1133) code(1026) }
{ inform(2794) health(2639) internet(1427) }
{ measur(2081) correl(1212) valu(896) }
{ bind(1733) structur(1185) ligand(1036) }
{ sequenc(1873) structur(1644) protein(1328) }
{ imag(2830) propos(1344) filter(1198) }
{ patient(2315) diseas(1263) diabet(1191) }
{ take(945) account(800) differ(722) }
{ motion(1329) object(1292) video(1091) }
{ assess(1506) score(1403) qualiti(1306) }
{ treatment(1704) effect(941) patient(846) }
{ surgeri(1148) surgic(1085) robot(1054) }
{ framework(1458) process(801) describ(734) }
{ chang(1828) time(1643) increas(1301) }
{ concept(1167) ontolog(924) domain(897) }
{ extract(1171) text(1153) clinic(932) }
{ data(1714) softwar(1251) tool(1186) }
{ care(1570) inform(1187) nurs(1089) }
{ featur(1941) imag(1645) propos(1176) }
{ risk(3053) factor(974) diseas(938) }
{ perform(999) metric(946) measur(919) }
{ system(1050) medic(1026) inform(1018) }
{ import(1318) role(1303) understand(862) }
{ visual(1396) interact(850) tool(830) }
{ compound(1573) activ(1297) structur(1058) }
{ perform(1367) use(1326) method(1137) }
{ spatial(1525) area(1432) region(1030) }
{ record(1888) medic(1808) patient(1693) }
{ health(3367) inform(1360) care(1135) }
{ monitor(1329) mobil(1314) devic(1160) }
{ ehr(2073) health(1662) electron(1139) }
{ patient(2837) hospit(1953) medic(668) }
{ data(2317) use(1299) case(1017) }
{ age(1611) year(1155) adult(843) }
{ data(3008) multipl(1320) sourc(1022) }
{ intervent(3218) particip(2042) group(1664) }
{ activ(1138) subject(705) human(624) }
{ time(1939) patient(1703) rate(768) }
{ structur(1116) can(940) graph(676) }
{ high(1669) rate(1365) level(1280) }
{ cancer(2502) breast(956) screen(824) }
{ use(1733) differ(960) four(931) }
{ drug(1928) target(777) effect(648) }
{ result(1111) use(1088) new(759) }
{ decis(3086) make(1611) patient(1517) }
{ process(1125) use(805) approach(778) }
{ activ(1452) weight(1219) physic(1104) }
{ method(1969) cluster(1462) data(1082) }
{ method(2212) result(1239) propos(1039) }

Resumo

JECTIVE: An electroencephalogram-based (EEG-based) brain-computer-interface (BCI) provides a new communication channel between the human brain and a computer. Amongst the various available techniques, artificial neural networks (ANNs) are well established in BCI research and have numerous successful applications. However, one of the drawbacks of conventional ANNs is the lack of an explicit input optimization mechanism. In addition, results of ANN learning are usually not easily interpretable. In this paper, we have applied an ANN-based method, the genetic neural mathematic method (GNMM), to two EEG channel selection and classification problems, aiming to address the issues above.METHODS AND MATERIALS: Pre-processing steps include: least-square (LS) approximation to determine the overall signal increase/decrease rate; locally weighted polynomial regression (Loess) and fast Fourier transform (FFT) to smooth the signals to determine the signal strength and variations. The GNMM method consists of three successive steps: (1) a genetic algorithm-based (GA-based) input selection process; (2) multi-layer perceptron-based (MLP-based) modelling; and (3) rule extraction based upon successful training. The fitness function used in the GA is the training error when an MLP is trained for a limited number of epochs. By averaging the appearance of a particular channel in the winning chromosome over several runs, we were able to minimize the error due to randomness and to obtain an energy distribution around the scalp. In the second step, a threshold was used to select a subset of channels to be fed into an MLP, which performed modelling with a large number of iterations, thus fine-tuning the input/output relationship. Upon successful training, neurons in the input layer are divided into four sub-spaces to produce if-then rules (step 3). Two datasets were used as case studies to perform three classifications. The first data were electrocorticography (ECoG) recordings that have been used in the BCI competition III. The data belonged to two categories, imagined movements of either a finger or the tongue. The data were recorded using an 8 ? 8 ECoG platinum electrode grid at a sampling rate of 1000 Hz for a total of 378 trials. The second dataset consisted of a 32-channel, 256 Hz EEG recording of 960 trials where participants had to execute a left- or right-hand button-press in response to left- or right-pointing arrow stimuli. The data were used to classify correct/incorrect responses and left/right hand movements.RESULTS: For the first dataset, 100 samples were reserved for testing, and those remaining were for training and validation with a ratio of 90%:10% using K-fold cross-validation. Using the top 10 channels selected by GNMM, we achieved a classification accuracy of 0.80 ? 0.04 for the testing dataset, which compares favourably with results reported in the literature. For the second case, we performed multi-time-windows pre-processing over a single trial. By selecting 6 channels out of 32, we were able to achieve a classification accuracy of about 0.86 for the response correctness classification and 0.82 for the actual responding hand classification, respectively. Furthermore, 139 regression rules were identified after training was completed.CONCLUSIONS: We demonstrate that GNMM is able to perform effective channel selections/reductions, which not only reduces the difficulty of data collection, but also greatly improves the generalization of the classifier. An important step that affects the effectiveness of GNMM is the pre-processing method. In this paper, we also highlight the importance of choosing an appropriate time window position.

Resumo Limpo

jectiv electroencephalogrambas eegbas braincomputerinterfac bci provid new communic channel human brain comput amongst various avail techniqu artifici neural network ann well establish bci research numer success applic howev one drawback convent ann lack explicit input optim mechan addit result ann learn usual easili interpret paper appli annbas method genet neural mathemat method gnmm two eeg channel select classif problem aim address issu abovemethod materi preprocess step includ leastsquar ls approxim determin overal signal increasedecreas rate local weight polynomi regress loess fast fourier transform fft smooth signal determin signal strength variat gnmm method consist three success step genet algorithmbas gabas input select process multilay perceptronbas mlpbase model rule extract base upon success train fit function use ga train error mlp train limit number epoch averag appear particular channel win chromosom sever run abl minim error due random obtain energi distribut around scalp second step threshold use select subset channel fed mlp perform model larg number iter thus finetun inputoutput relationship upon success train neuron input layer divid four subspac produc ifthen rule step two dataset use case studi perform three classif first data electrocorticographi ecog record use bci competit iii data belong two categori imagin movement either finger tongu data record use ecog platinum electrod grid sampl rate hz total trial second dataset consist channel hz eeg record trial particip execut left righthand buttonpress respons left rightpoint arrow stimuli data use classifi correctincorrect respons leftright hand movementsresult first dataset sampl reserv test remain train valid ratio use kfold crossvalid use top channel select gnmm achiev classif accuraci test dataset compar favour result report literatur second case perform multitimewindow preprocess singl trial select channel abl achiev classif accuraci respons correct classif actual respond hand classif respect furthermor regress rule identifi train completedconclus demonstr gnmm abl perform effect channel selectionsreduct reduc difficulti data collect also great improv general classifi import step affect effect gnmm preprocess method paper also highlight import choos appropri time window posit

Resumos Similares

Comput Methods Programs Biomed - Classification of normal and epileptic seizure EEG signals using wavelet transform, phase-space reconstruction, and Euclidean distance. ( 0,715309273516956 )
J Med Syst - Applying cybernetic technology to diagnose human pulmonary sounds. ( 0,699880717411509 )
Comput Methods Programs Biomed - Classification of the electrocardiogram signals using supervised classifiers and efficient features. ( 0,699037739890672 )
Int J Neural Syst - Combination of heterogeneous EEG feature extraction methods and stacked sequential learning for sleep stage classification. ( 0,698234836691702 )
Comput. Biol. Med. - Noninvasive detection of mechanical prosthetic heart valve disorder. ( 0,696830106611107 )
Med Biol Eng Comput - Feature selection on movement imagery discrimination and attention detection. ( 0,695999647796647 )
Comput Methods Programs Biomed - Clustering technique-based least square support vector machine for EEG signal classification. ( 0,687941584662265 )
Med Biol Eng Comput - Predicting termination of paroxysmal atrial fibrillation using empirical mode decomposition of the atrial activity and statistical features of the heart rate variability. ( 0,685517499513403 )
Comput. Biol. Med. - Odorant recognition using biological responses recorded in olfactory bulb of rats. ( 0,682757752572825 )
Med Biol Eng Comput - Wavelet-based sparse functional linear model with applications to EEGs seizure detection and epilepsy diagnosis. ( 0,677409662161585 )
Comput. Biol. Med. - A novel real-time patient-specific seizure diagnosis algorithm based on analysis of EEG and ECG signals using spectral and spatial features and improved particle swarm optimization classifier. ( 0,673527195689125 )
Neural Comput - A theoretical basis for emergent pattern discrimination in neural systems through slow feature extraction. ( 0,671504038464775 )
J Med Syst - Employment and comparison of different Artificial Neural Networks for epilepsy diagnosis from EEG signals. ( 0,670998079582277 )
J Med Syst - Effect of multiscale PCA de-noising on EMG signal classification for diagnosis of neuromuscular disorders. ( 0,670989808646743 )
Med Biol Eng Comput - SEMG-based hand motion recognition using cumulative residual entropy and extreme learning machine. ( 0,67047689257413 )
Comput. Biol. Med. - Self-evaluated automatic classifier as a decision-support tool for sleep/wake staging. ( 0,668170523736462 )
J Med Syst - Detection of carotid artery disease by using Learning Vector Quantization Neural Network. ( 0,661046966998093 )
J Med Syst - A biomedical system based on artificial neural network and principal component analysis for diagnosis of the heart valve diseases. ( 0,657290165224225 )
Artif Intell Med - Kernel machines for epilepsy diagnosis via EEG signal classification: a comparative study. ( 0,656774331165949 )
Int J Comput Assist Radiol Surg - Ultrasound texture-based CAD system for detecting neuromuscular diseases. ( 0,656171760913547 )
Comput Methods Programs Biomed - Prediction of paroxysmal atrial fibrillation based on non-linear analysis and spectrum and bispectrum features of the heart rate variability signal. ( 0,655212705359767 )
Comput. Biol. Med. - Automatic sleep staging from ventilator signals in non-invasive ventilation. ( 0,653078628438716 )
Comput. Biol. Med. - Assessment of multichannel lung sounds parameterization for two-class classification in interstitial lung disease patients. ( 0,651405627421275 )
J Med Syst - Artificial apnea classification with quantitative sleep EEG synchronization. ( 0,649884849109448 )
Comput. Biol. Med. - Classification of EMG signals using PSO optimized SVM for diagnosis of neuromuscular disorders. ( 0,648550184938879 )
Artif Intell Med - Development of electroencephalographic pattern classifiers for real and imaginary thumb and index finger movements of one hand. ( 0,648019823594623 )
Med Biol Eng Comput - Pathological speech signal analysis and classification using empirical mode decomposition. ( 0,646640268607762 )
Med Biol Eng Comput - Classification of multichannel EEG patterns using parallel hidden Markov models. ( 0,646079086070286 )
J Med Syst - Diagnosis of epilepsy from electroencephalography signals using multilayer perceptron and Elman Artificial Neural Networks and Wavelet Transform. ( 0,644282460549257 )
Artif Intell Med - Supervised machine learning-based classification of oral malodor based on the microbiota in saliva samples. ( 0,639074250431614 )
Int J Neural Syst - Application of higher order cumulant features for cardiac health diagnosis using ECG signals. ( 0,637981097237357 )
Neural Comput - Kernels for longitudinal data with variable sequence length and sampling intervals. ( 0,635160556467526 )
Int J Neural Syst - Automated diagnosis of epilepsy using CWT, HOS and texture parameters. ( 0,634680530966481 )
Comput. Biol. Med. - A multi-stage automatic arrhythmia recognition and classification system. ( 0,634619809040242 )
Comput Methods Programs Biomed - Functional activity maps based on significance measures and Independent Component Analysis. ( 0,630490351071411 )
Int J Neural Syst - Efficient automatic selection and combination of EEG features in least squares classifiers for motor imagery brain-computer interfaces. ( 0,630032113695888 )
Comput Methods Programs Biomed - Feature extraction for ECG heartbeats using higher order statistics of WPD coefficients. ( 0,626146273400178 )
IEEE J Biomed Health Inform - Support vector machine classification based on correlation prototypes applied to bone age assessment. ( 0,625836728828163 )
Comput Methods Programs Biomed - Automatic classification of the interferential tear film lipid layer using colour texture analysis. ( 0,625524252519855 )
J Clin Monit Comput - Identification of apnea during respiratory monitoring using support vector machine classifier: a pilot study. ( 0,624391495073644 )
J Med Syst - Automatic and adaptive classification of electroencephalographic signals for brain computer interfaces. ( 0,622494529617109 )
J Med Syst - Analysis of infant cry through weighted linear prediction cepstral coefficients and Probabilistic Neural Network. ( 0,621110187714922 )
Int J Neural Syst - Comparison of ictal and interictal EEG signals using fractal features. ( 0,619370096273866 )
Int J Neural Syst - Application of quantum-behaved particle swarm optimization to motor imagery EEG classification. ( 0,61806971867542 )
Comput Math Methods Med - An expert system based on Fisher score and LS-SVM for cardiac arrhythmia diagnosis. ( 0,617068758104838 )
Comput. Biol. Med. - Neurocognitive disorder detection based on feature vectors extracted from VBM analysis of structural MRI. ( 0,616730828392519 )
Int J Neural Syst - Single-trial motor imagery classification using asymmetry ratio, phase relation, wavelet-based fractal, and their selected combination. ( 0,616165587700174 )
Comput Methods Programs Biomed - Neural network and wavelet average framing percentage energy for atrial fibrillation classification. ( 0,615731513776195 )
Comput Methods Programs Biomed - Automatic classification of sleep stages based on the time-frequency image of EEG signals. ( 0,615371294267341 )
Comput. Biol. Med. - An experimental comparison of gene selection by Lasso and Dantzig selector for cancer classification. ( 0,615047091726674 )
BMC Med Inform Decis Mak - Effective diagnosis of Alzheimer's disease by means of large margin-based methodology. ( 0,613209030575111 )
Comput. Biol. Med. - Medical decision support system for diagnosis of neuromuscular disorders using DWT and fuzzy support vector machines. ( 0,612762375117584 )
Med Biol Eng Comput - Signal feature extraction by multi-scale PCA and its application to respiratory sound classification. ( 0,612253528045021 )
Comput. Biol. Med. - Automatic classification of infant sleep based on instantaneous frequencies in a single-channel EEG signal. ( 0,612122016583666 )
Comput Methods Programs Biomed - Complex extreme learning machine applications in terahertz pulsed signals feature sets. ( 0,609960724217243 )
J Med Syst - Classification of epilepsy using high-order spectra features and principle component analysis. ( 0,608973847624577 )
J Med Syst - A software framework for building biomedical machine learning classifiers through grid computing resources. ( 0,606209318691291 )
Comput. Biol. Med. - Using phase space reconstruction for patient independent heartbeat classification in comparison with some benchmark methods. ( 0,605586317107275 )
J Clin Monit Comput - Classification of sleep apnea types using wavelet packet analysis of short-term ECG signals. ( 0,605215481615159 )
J Med Syst - Luminance sticker based facial expression recognition using discrete wavelet transform for physically disabled persons. ( 0,605206185384431 )
J Clin Monit Comput - Prognostic value of EEG indexes for the Glasgow outcome scale of comatose patients in the acute phase. ( 0,604489463200146 )
Comput Math Methods Med - Comparison of the data classification approaches to diagnose spinal cord injury. ( 0,601508717128083 )
Comput. Biol. Med. - Ant colony optimization-based feature selection method for surface electromyography signals classification. ( 0,599862626538492 )
J Med Syst - A new method based on Adaptive Discrete Wavelet Entropy Energy and Neural Network Classifier (ADWEENN) for recognition of urine cells from microscopic images independent of rotation and scaling. ( 0,598281778352207 )
Med Biol Eng Comput - Voiceless Arabic vowels recognition using facial EMG. ( 0,597021629738397 )
Artif Intell Med - Comparative analysis of a-priori and a-posteriori dietary patterns using state-of-the-art classification algorithms: a case/case-control study. ( 0,595795001247651 )
Comput Methods Programs Biomed - Automatic sleep staging using empirical mode decomposition, discrete wavelet transform, time-domain, and nonlinear dynamics features of heart rate variability signals. ( 0,595632544812422 )
IEEE J Biomed Health Inform - Automatic detection of atrial fibrillation in cardiac vibration signals. ( 0,595180417531516 )
J Med Syst - A new QRS detection method using wavelets and artificial neural networks. ( 0,594696226901636 )
J Med Syst - Application of higher order spectra to identify epileptic EEG. ( 0,591589611031099 )
Comput. Biol. Med. - Comparison of different EEG features in estimation of hypnosis susceptibility level. ( 0,590412952671486 )
Comput Math Methods Med - Knee joint vibration signal analysis with matching pursuit decomposition and dynamic weighted classifier fusion. ( 0,589915243610908 )
Brief. Bioinformatics - Class-imbalanced classifiers for high-dimensional data. ( 0,589850802772339 )
Med Biol Eng Comput - Application of recurrence quantification analysis to automatically estimate infant sleep states using a single channel of respiratory data. ( 0,589625316233978 )
Med Biol Eng Comput - Evaluation of feature extraction methods for EEG-based brain-computer interfaces in terms of robustness to slight changes in electrode locations. ( 0,589399342947409 )
Comput. Biol. Med. - Feature extraction and recognition of ictal EEG using EMD and SVM. ( 0,589067353774179 )
Artif Intell Med - Selection of effective features for ECG beat recognition based on nonlinear correlations. ( 0,588977678679126 )
Methods Inf Med - Imaging the thoracic distribution of normal breath sounds. ( 0,588215345523084 )
Int J Neural Syst - Improved adaptive splitting and selection: the hybrid training method of a classifier based on a feature space partitioning. ( 0,587205483930223 )
Comput. Biol. Med. - A classification system based on a new wrapper feature selection algorithm for the diagnosis of primary and secondary polycythemia. ( 0,585463192166399 )
Med Biol Eng Comput - Automated detection of obstructive sleep apnoea syndrome from oxygen saturation recordings using linear discriminant analysis. ( 0,584113385592711 )
Med Biol Eng Comput - Efficient automatic classifiers for the detection of A phases of the cyclic alternating pattern in sleep. ( 0,58379502153315 )
Artif Intell Med - Electrocardiogram analysis using a combination of statistical, geometric, and nonlinear heart rate variability features. ( 0,583380229495555 )
Comput Methods Programs Biomed - A model-based method for computation of correlation dimension, Lyapunov exponents and synchronization from depth-EEG signals. ( 0,583178829942399 )
Int J Neural Syst - Application of empirical mode decomposition (emd) for automated detection of epilepsy using EEG signals. ( 0,582792688913752 )
J Med Syst - Singular value decomposition based feature extraction technique for physiological signal analysis. ( 0,581901050580391 )
Comput Methods Programs Biomed - Classifying depression patients and normal subjects using machine learning techniques and nonlinear features from EEG signal. ( 0,580740780569201 )
J Med Syst - A comparative study on classification of sleep stage based on EEG signals using feature selection and classification algorithms. ( 0,579740697273744 )
Comput. Biol. Med. - Sparse maximum margin discriminant analysis for feature extraction and gene selection on gene expression data. ( 0,579738271017154 )
Comput. Biol. Med. - Gene expression microarray classification using PCA-BEL. ( 0,579383242402961 )
Artif Intell Med - Automatic detection of epileptic seizures on the intra-cranial electroencephalogram of rats using reservoir computing. ( 0,578855499463506 )
Int J Neural Syst - On the segmentation and classification of hand radiographs. ( 0,576983949482944 )
J Med Syst - Classification of normal and diseased liver shapes based on Spherical Harmonics coefficients. ( 0,576234863874743 )
Comput Math Methods Med - An intelligent system approach for asthma prediction in symptomatic preschool children. ( 0,575570936262564 )
Comput Methods Programs Biomed - Influence of QRS complex detection errors on entropy algorithms. Application to heart rate variability discrimination. ( 0,575491674670411 )
Comput Math Methods Med - Principal feature analysis: a multivariate feature selection method for fMRI data. ( 0,575174980593603 )
IEEE J Biomed Health Inform - Extracting and Selecting Distinctive EEG Features for Efficient Epileptic Seizure Prediction. ( 0,574487176473665 )
Comput Methods Programs Biomed - ECG beat classification using a cost sensitive classifier. ( 0,574135264315496 )
Comput. Biol. Med. - Mammographical mass detection and classification using local seed region growing-spherical wavelet transform (LSRG-SWT) hybrid scheme. ( 0,573841685907927 )
Comput Math Methods Med - Multivoxel pattern analysis for FMRI data: a review. ( 0,573815337856962 )