Displaying publications 41 - 60 of 67 in total

Abstract:
Sort:
  1. Halder D, Quah BS, Malik AS, Choo KE
    PMID: 9185277
    Neonatal septic arthritis has always been considered as separate from its counterpart in older children. The condition is uncommon but serious. Affected neonates usually survive, but with permanent skeletal deformities. Ten cases of neonatal septic arthritis were diagnosed between January 1989 and December 1993 in the neonatal intensive care units of two referral hospitals in the state of Kelantan, Malaysia. All except one neonate was born prematurely. The mean age of presentation was 15.6 days. Joint swelling (10/10), increased warmth (7/10) and erythema of the overlying skin (7/10) were the common presenting signs. Vague constitutional symptoms preceded the definitive signs of septic arthritis in all cases. The total white cell counts were raised with shift to the left. The knee (60%) was not commonly affected, followed by the hip (13%) and ankle (13%). Three neonates had multiple joint involvement. Coexistence of arthritis with osteomyelitis was observed in seven neonates. The commonest organism isolated was methicillin resistant Staphylococcus aureus (9/10). Needle aspiration was performed in nine neonates and one had incision with drainage. Follow up data was available for five neonates and two of these had skeletal morbidity. Early diagnosis by frequent examination of the joints, prompt treatment and control of nosocomial infection are important for management.
  2. Malik AS, Ram SP, Seng QB, Noor AR
    Ann Acad Med Singap, 1994 Nov;23(6):914-6.
    PMID: 7741513
    We describe two Malay male term neonates with congenital limb reduction defects. The first neonate had hypodactyly of limbs associated with micrognathia, microstomia, glossopalatine ankylosis and congenital mitral stenosis. He developed gram-negative septicaemia and died on day 14 of life. The second neonate had tetraperomelia without any other associated congenital abnormality. He developed staphylococcal skin infection which was treated conservatively. Very few cases of congenital limb reduction defects have been reported in the Asian population and we are not aware of any other reports describing Malay infants with the congenital abnormalities described in this report.
  3. Sherazi ZA, Abdullah AW, Malik AS, Saad R
    Ann Acad Med Singap, 1993 Sep;22(5):701-6.
    PMID: 8267349
    To assess the utility of the current imaging modalities, a six-year retrospective study was conducted from May 1985 through April 1991 on 11 patients with histopathologically confirmed neuroblastoma. There were four males and seven females. Median age at presentation was six years. All patients underwent intravenous urography (IVU), abdominal ultrasonography (US), skeletal surveys and bone marrow aspiration. Computed tomographic (CT) scanning was performed in nine patients and trephine bone biopsy in five. Suprarenal gland was the primary site in six patients, including one bilateral neuroblastoma. Two presented with primary paraspinal mass, one with posterior mediastinal mass, one had a retroperitoneal tumour and one presented as primary cerebral neuroblastoma. IVU showed indirect evidence of suprarenal tumours in five patients. US demonstrated suprarenal mass in six and calcification within the mass in five patients. US also documented retroperitoneal lymphadenopathy in five patients. US-guided fine needle aspiration biopsy was performed in seven patients and it gave correct histological diagnosis in all. CT accurately depicted all the primary tumours and their involvement of the surrounding structures and metastases in the brain and orbits. US proved to be quite accurate in diagnosing primary abdominal tumours despite its limitations but in other sites, CT was of greater help. Solid appearance of a suprarenal mass on US made the diagnosis of neuroblastoma very likely and calcification within the mass further supported the diagnosis.
  4. Khan MB, Lee XY, Nisar H, Ng CA, Yeap KH, Malik AS
    Adv Exp Med Biol, 2015;823:227-48.
    PMID: 25381111 DOI: 10.1007/978-3-319-10984-8_13
    Activated sludge system is generally used in wastewater treatment plants for processing domestic influent. Conventionally the activated sludge wastewater treatment is monitored by measuring physico-chemical parameters like total suspended solids (TSSol), sludge volume index (SVI) and chemical oxygen demand (COD) etc. For the measurement, tests are conducted in the laboratory, which take many hours to give the final measurement. Digital image processing and analysis offers a better alternative not only to monitor and characterize the current state of activated sludge but also to predict the future state. The characterization by image processing and analysis is done by correlating the time evolution of parameters extracted by image analysis of floc and filaments with the physico-chemical parameters. This chapter briefly reviews the activated sludge wastewater treatment; and, procedures of image acquisition, preprocessing, segmentation and analysis in the specific context of activated sludge wastewater treatment. In the latter part additional procedures like z-stacking, image stitching are introduced for wastewater image preprocessing, which are not previously used in the context of activated sludge. Different preprocessing and segmentation techniques are proposed, along with the survey of imaging procedures reported in the literature. Finally the image analysis based morphological parameters and correlation of the parameters with regard to monitoring and prediction of activated sludge are discussed. Hence it is observed that image analysis can play a very useful role in the monitoring of activated sludge wastewater treatment plants.
  5. Nisar H, Malik AS, Ullah R, Shim SO, Bawakid A, Khan MB, et al.
    Adv Exp Med Biol, 2015;823:159-74.
    PMID: 25381107 DOI: 10.1007/978-3-319-10984-8_9
    The fundamental step in brain research deals with recording electroencephalogram (EEG) signals and then investigating the recorded signals quantitatively. Topographic EEG (visual spatial representation of EEG signal) is commonly referred to as brain topomaps or brain EEG maps. In this chapter, full search full search block motion estimation algorithm has been employed to track the brain activity in brain topomaps to understand the mechanism of brain wiring. The behavior of EEG topomaps is examined throughout a particular brain activation with respect to time. Motion vectors are used to track the brain activation over the scalp during the activation period. Using motion estimation it is possible to track the path from the starting point of activation to the final point of activation. Thus it is possible to track the path of a signal across various lobes.
  6. Amin HU, Malik AS, Ahmad RF, Badruddin N, Kamel N, Hussain M, et al.
    Australas Phys Eng Sci Med, 2015 Mar;38(1):139-49.
    PMID: 25649845 DOI: 10.1007/s13246-015-0333-x
    This paper describes a discrete wavelet transform-based feature extraction scheme for the classification of EEG signals. In this scheme, the discrete wavelet transform is applied on EEG signals and the relative wavelet energy is calculated in terms of detailed coefficients and the approximation coefficients of the last decomposition level. The extracted relative wavelet energy features are passed to classifiers for the classification purpose. The EEG dataset employed for the validation of the proposed method consisted of two classes: (1) the EEG signals recorded during the complex cognitive task--Raven's advance progressive metric test and (2) the EEG signals recorded in rest condition--eyes open. The performance of four different classifiers was evaluated with four performance measures, i.e., accuracy, sensitivity, specificity and precision values. The accuracy was achieved above 98 % by the support vector machine, multi-layer perceptron and the K-nearest neighbor classifiers with approximation (A4) and detailed coefficients (D4), which represent the frequency range of 0.53-3.06 and 3.06-6.12 Hz, respectively. The findings of this study demonstrated that the proposed feature extraction approach has the potential to classify the EEG signals recorded during a complex cognitive task by achieving a high accuracy rate.
  7. Hani AF, Kumar D, Malik AS, Walter N, Razak R, Kiflie A
    Acad Radiol, 2015 Jan;22(1):93-104.
    PMID: 25481518 DOI: 10.1016/j.acra.2014.08.008
    Quantitative assessment of knee articular cartilage (AC) morphology using magnetic resonance (MR) imaging requires an accurate segmentation and 3D reconstruction. However, automatic AC segmentation and 3D reconstruction from hydrogen-based MR images alone is challenging because of inhomogeneous intensities, shape irregularity, and low contrast existing in the cartilage region. Thus, the objective of this research was to provide an insight into morphologic assessment of AC using multilevel data processing of multinuclear ((23)Na and (1)H) MR knee images.
  8. Hani AF, Kumar D, Malik AS, Ahmad RM, Razak R, Kiflie A
    Rheumatol Int, 2015 Jan;35(1):1-16.
    PMID: 24879325 DOI: 10.1007/s00296-014-3052-9
    Early detection of knee osteoarthritis (OA) is of great interest to orthopaedic surgeons, rheumatologists, radiologists, and researchers because it would allow physicians to provide patients with treatments and advice to slow the onset or progression of the disease. Early detection can be achieved by identifying early changes in selected features of degenerative articular cartilage (AC) using non-invasive imaging modalities. Magnetic resonance imaging (MRI) is becoming the standard for assessment of OA. The aim of this paper was to review the influence of MRI on the selection, detection, and measurement of AC features associated with early OA. Our review of the literature indicates that the changes associated with early OA are in cartilage thickness, cartilage volume, cartilage water content, and proteoglycan content that can be accurately, consistently, and non-invasively measured using MRI. Choosing an MR pulse sequence that provides the capability to assess cartilage physiology and morphology in a single acquisition and advanced multi-nuclei MRI is desirable. The results of the review indicate that using an ultra-high magnetic strength, MR imager does not affect early OA detection. In conclusion, MRI is currently the most suitable modality for early detection of knee OA, and future research should focus on the quantitative evaluation of early OA features using advances in MR hardware, software, and data processing with sophisticated image/pattern recognition techniques.
  9. Amin HU, Malik AS, Kamel N, Chooi WT, Hussain M
    J Neuroeng Rehabil, 2015;12:87.
    PMID: 26400233 DOI: 10.1186/s12984-015-0077-6
    Educational psychology research has linked fluid intelligence with learning and memory abilities and neuroimaging studies have specifically associated fluid intelligence with event related potentials (ERPs). The objective of this study is to find the relationship of ERPs with learning and memory recall and predict the memory recall score using P300 (P3) component.
  10. Ahmad RF, Malik AS, Kamel N, Reza F, Abdullah JM
    Australas Phys Eng Sci Med, 2016 Jun;39(2):363-78.
    PMID: 27043850 DOI: 10.1007/s13246-016-0438-x
    Memory plays an important role in human life. Memory can be divided into two categories, i.e., long term memory and short term memory (STM). STM or working memory (WM) stores information for a short span of time and it is used for information manipulations and fast response activities. WM is generally involved in the higher cognitive functions of the brain. Different studies have been carried out by researchers to understand the WM process. Most of these studies were based on neuroimaging modalities like fMRI, EEG, MEG etc., which use standalone processes. Each neuroimaging modality has some pros and cons. For example, EEG gives high temporal resolution but poor spatial resolution. On the other hand, the fMRI results have a high spatial resolution but poor temporal resolution. For a more in depth understanding and insight of what is happening inside the human brain during the WM process or during cognitive tasks, high spatial as well as high temporal resolution is desirable. Over the past decade, researchers have been working to combine different modalities to achieve a high spatial and temporal resolution at the same time. Developments of MRI compatible EEG equipment in recent times have enabled researchers to combine EEG-fMRI successfully. The research publications in simultaneous EEG-fMRI have been increasing tremendously. This review is focused on the WM research involving simultaneous EEG-fMRI data acquisition and analysis. We have covered the simultaneous EEG-fMRI application in WM and data processing. Also, it adds to potential fusion methods which can be used for simultaneous EEG-fMRI for WM and cognitive tasks.
  11. Zafar R, Malik AS, Kamel N, Dass SC, Abdullah JM, Reza F, et al.
    J Integr Neurosci, 2015 Jun;14(2):155-68.
    PMID: 25939499 DOI: 10.1142/S0219635215500089
    Brain is the command center for the body and contains a lot of information which can be extracted by using different non-invasive techniques. Electroencephalography (EEG), Magnetoencephalography (MEG) and functional magnetic resonance imaging (fMRI) are the most common neuroimaging techniques to elicit brain behavior. By using these techniques different activity patterns can be measured within the brain to decode the content of mental processes especially the visual and auditory content. This paper discusses the models and imaging techniques used in visual decoding to investigate the different conditions of brain along with recent advancements in brain decoding. This paper concludes that it's not possible to extract all the information from the brain, however careful experimentation, interpretation and powerful statistical tools can be used with the neuroimaging techniques for better results.
  12. Ahmad RF, Malik AS, Kamel N, Reza F, Amin HU, Hussain M
    Technol Health Care, 2017;25(3):471-485.
    PMID: 27935575 DOI: 10.3233/THC-161286
    BACKGROUND: Classification of the visual information from the brain activity data is a challenging task. Many studies reported in the literature are based on the brain activity patterns using either fMRI or EEG/MEG only. EEG and fMRI considered as two complementary neuroimaging modalities in terms of their temporal and spatial resolution to map the brain activity. For getting a high spatial and temporal resolution of the brain at the same time, simultaneous EEG-fMRI seems to be fruitful.

    METHODS: In this article, we propose a new method based on simultaneous EEG-fMRI data and machine learning approach to classify the visual brain activity patterns. We acquired EEG-fMRI data simultaneously on the ten healthy human participants by showing them visual stimuli. Data fusion approach is used to merge EEG and fMRI data. Machine learning classifier is used for the classification purposes.

    RESULTS: Results showed that superior classification performance has been achieved with simultaneous EEG-fMRI data as compared to the EEG and fMRI data standalone. This shows that multimodal approach improved the classification accuracy results as compared with other approaches reported in the literature.

    CONCLUSIONS: The proposed simultaneous EEG-fMRI approach for classifying the brain activity patterns can be helpful to predict or fully decode the brain activity patterns.

  13. Zafar R, Kamel N, Naufal M, Malik AS, Dass SC, Ahmad RF, et al.
    Australas Phys Eng Sci Med, 2018 Sep;41(3):633-645.
    PMID: 29948968 DOI: 10.1007/s13246-018-0656-5
    Neuroscientists have investigated the functionality of the brain in detail and achieved remarkable results but this area still need further research. Functional magnetic resonance imaging (fMRI) is considered as the most reliable and accurate technique to decode the human brain activity, on the other hand electroencephalography (EEG) is a portable and low cost solution in brain research. The purpose of this study is to find whether EEG can be used to decode the brain activity patterns like fMRI. In fMRI, data from a very specific brain region is enough to decode the brain activity patterns due to the quality of data. On the other hand, EEG can measure the rapid changes in neuronal activity patterns due to its higher temporal resolution i.e., in msec. These rapid changes mostly occur in different brain regions. In this study, multivariate pattern analysis (MVPA) is used both for EEG and fMRI data analysis and the information is extracted from distributed activation patterns of the brain. The significant information among different classes is extracted using two sample t test in both data sets. Finally, the classification analysis is done using the support vector machine. A fair comparison of both data sets is done using the same analysis techniques, moreover simultaneously collected data of EEG and fMRI is used for this comparison. The final analysis is done with the data of eight participants; the average result of all conditions are found which is 65.7% for EEG data set and 64.1% for fMRI data set. It concludes that EEG is capable of doing brain decoding with the data from multiple brain regions. In other words, decoding accuracy with EEG MVPA is as good as fMRI MVPA and is above chance level.
  14. Mumtaz W, Vuong PL, Xia L, Malik AS, Rashid RBA
    Cogn Neurodyn, 2017 Apr;11(2):161-171.
    PMID: 28348647 DOI: 10.1007/s11571-016-9416-y
    Screening alcohol use disorder (AUD) patients has been challenging due to the subjectivity involved in the process. Hence, robust and objective methods are needed to automate the screening of AUD patients. In this paper, a machine learning method is proposed that utilized resting-state electroencephalography (EEG)-derived features as input data to classify the AUD patients and healthy controls and to perform automatic screening of AUD patients. In this context, the EEG data were recorded during 5 min of eyes closed and 5 min of eyes open conditions. For this purpose, 30 AUD patients and 15 aged-matched healthy controls were recruited. After preprocessing the EEG data, EEG features such as inter-hemispheric coherences and spectral power for EEG delta, theta, alpha, beta and gamma bands were computed involving 19 scalp locations. The selection of most discriminant features was performed with a rank-based feature selection method assigning a weight value to each feature according to a criterion, i.e., receiver operating characteristics curve. For example, a feature with large weight was considered more relevant to the target labels than a feature with less weight. Therefore, a reduced set of most discriminant features was identified and further be utilized during classification of AUD patients and healthy controls. As results, the inter-hemispheric coherences between the brain regions were found significantly different between the study groups and provided high classification efficiency (Accuracy = 80.8,sensitivity = 82.5,and specificity = 80,F-Measure = 0.78). In addition, the power computed in different EEG bands were found significant and provided an overall classification efficiency as (Accuracy = 86.6,sensitivity = 95,specificity = 82.5,and F-Measure = 0.88). Further, the integration of these EEG feature resulted into even higher results (Accuracy = 89.3 %,sensitivity = 88.5 %,specificity = 91 %,and F-Measure = 0.90). Based on the results, it is concluded that the EEG data (integration of the theta, beta, and gamma power and inter-hemispheric coherence) could be utilized as objective markers to screen the AUD patients and healthy controls.
  15. Qazi EU, Hussain M, Aboalsamh H, Malik AS, Amin HU, Bamatraf S
    Front Hum Neurosci, 2016;10:687.
    PMID: 28163676 DOI: 10.3389/fnhum.2016.00687
    Assessing a person's intelligence level is required in many situations, such as career counseling and clinical applications. EEG evoked potentials in oddball task and fluid intelligence score are correlated because both reflect the cognitive processing and attention. A system for prediction of an individual's fluid intelligence level using single trial Electroencephalography (EEG) signals has been proposed. For this purpose, we employed 2D and 3D contents and 34 subjects each for 2D and 3D, which were divided into low-ability (LA) and high-ability (HA) groups using Raven's Advanced Progressive Matrices (RAPM) test. Using visual oddball cognitive task, neural activity of each group was measured and analyzed over three midline electrodes (Fz, Cz, and Pz). To predict whether an individual belongs to LA or HA group, features were extracted using wavelet decomposition of EEG signals recorded in visual oddball task and support vector machine (SVM) was used as a classifier. Two different types of Haar wavelet transform based features have been extracted from the band (0.3 to 30 Hz) of EEG signals. Statistical wavelet features and wavelet coefficient features from the frequency bands 0.0-1.875 Hz (delta low) and 1.875-3.75 Hz (delta high), resulted in the 100 and 98% prediction accuracies, respectively, both for 2D and 3D contents. The analysis of these frequency bands showed clear difference between LA and HA groups. Further, discriminative values of the features have been validated using statistical significance tests and inter-class and intra-class variation analysis. Also, statistical test showed that there was no effect of 2D and 3D content on the assessment of fluid intelligence level. Comparisons with state-of-the-art techniques showed the superiority of the proposed system.
  16. Elaina NS, Malik AS, Shams WK, Badruddin N, Abdullah JM, Reza MF
    Clin Neuroradiol, 2018 Jun;28(2):267-281.
    PMID: 28116447 DOI: 10.1007/s00062-017-0557-0
    PURPOSE: To localize sensorimotor cortical activation in 10 patients with frontoparietal tumors using quantitative magnetoencephalography (MEG) with noise-normalized approaches.

    MATERIAL AND METHODS: Somatosensory evoked magnetic fields (SEFs) were elicited in 10 patients with somatosensory tumors and in 10 control participants using electrical stimulation of the median nerve via the right and left wrists. We localized the N20m component of the SEFs using dynamic statistical parametric mapping (dSPM) and standardized low-resolution brain electromagnetic tomography (sLORETA) combined with 3D magnetic resonance imaging (MRI). The obtained coordinates were compared between groups. Finally, we statistically evaluated the N20m parameters across hemispheres using non-parametric statistical tests.

    RESULTS: The N20m sources were accurately localized to Brodmann area 3b in all members of the control group and in seven of the patients; however, the sources were shifted in three patients relative to locations outside the primary somatosensory cortex (SI). Compared with the affected (tumor) hemispheres in the patient group, N20m amplitudes and the strengths of the current sources were significantly lower in the unaffected hemispheres and in both hemispheres of the control group. These results were consistent for both dSPM and sLORETA approaches.

    CONCLUSION: Tumors in the sensorimotor cortex lead to cortical functional reorganization and an increase in N20m amplitude and current-source strengths. Noise-normalized approaches for MEG analysis that are integrated with MRI show accurate and reliable localization of sensorimotor function.

  17. Mumtaz W, Xia L, Mohd Yasin MA, Azhar Ali SS, Malik AS
    PLoS One, 2017;12(2):e0171409.
    PMID: 28152063 DOI: 10.1371/journal.pone.0171409
    Treatment management for Major Depressive Disorder (MDD) has been challenging. However, electroencephalogram (EEG)-based predictions of antidepressant's treatment outcome may help during antidepressant's selection and ultimately improve the quality of life for MDD patients. In this study, a machine learning (ML) method involving pretreatment EEG data was proposed to perform such predictions for Selective Serotonin Reuptake Inhibitor (SSRIs). For this purpose, the acquisition of experimental data involved 34 MDD patients and 30 healthy controls. Consequently, a feature matrix was constructed involving time-frequency decomposition of EEG data based on wavelet transform (WT) analysis, termed as EEG data matrix. However, the resultant EEG data matrix had high dimensionality. Therefore, dimension reduction was performed based on a rank-based feature selection method according to a criterion, i.e., receiver operating characteristic (ROC). As a result, the most significant features were identified and further be utilized during the training and testing of a classification model, i.e., the logistic regression (LR) classifier. Finally, the LR model was validated with 100 iterations of 10-fold cross-validation (10-CV). The classification results were compared with short-time Fourier transform (STFT) analysis, and empirical mode decompositions (EMD). The wavelet features extracted from frontal and temporal EEG data were found statistically significant. In comparison with other time-frequency approaches such as the STFT and EMD, the WT analysis has shown highest classification accuracy, i.e., accuracy = 87.5%, sensitivity = 95%, and specificity = 80%. In conclusion, significant wavelet coefficients extracted from frontal and temporal pre-treatment EEG data involving delta and theta frequency bands may predict antidepressant's treatment outcome for the MDD patients.
  18. Zafar R, Kamel N, Naufal M, Malik AS, Dass SC, Ahmad RF, et al.
    J Integr Neurosci, 2017;16(3):275-289.
    PMID: 28891512 DOI: 10.3233/JIN-170016
    Decoding of human brain activity has always been a primary goal in neuroscience especially with functional magnetic resonance imaging (fMRI) data. In recent years, Convolutional neural network (CNN) has become a popular method for the extraction of features due to its higher accuracy, however it needs a lot of computation and training data. In this study, an algorithm is developed using Multivariate pattern analysis (MVPA) and modified CNN to decode the behavior of brain for different images with limited data set. Selection of significant features is an important part of fMRI data analysis, since it reduces the computational burden and improves the prediction performance; significant features are selected using t-test. MVPA uses machine learning algorithms to classify different brain states and helps in prediction during the task. General linear model (GLM) is used to find the unknown parameters of every individual voxel and the classification is done using multi-class support vector machine (SVM). MVPA-CNN based proposed algorithm is compared with region of interest (ROI) based method and MVPA based estimated values. The proposed method showed better overall accuracy (68.6%) compared to ROI (61.88%) and estimation values (64.17%).
  19. Mumtaz W, Saad MNBM, Kamel N, Ali SSA, Malik AS
    Artif Intell Med, 2018 01;84:79-89.
    PMID: 29169647 DOI: 10.1016/j.artmed.2017.11.002
    BACKGROUND: The abnormal alcohol consumption could cause toxicity and could alter the human brain's structure and function, termed as alcohol used disorder (AUD). Unfortunately, the conventional screening methods for AUD patients are subjective and manual. Hence, to perform automatic screening of AUD patients, objective methods are needed. The electroencephalographic (EEG) data have been utilized to study the differences of brain signals between alcoholics and healthy controls that could further developed as an automatic screening tool for alcoholics.

    METHOD: In this work, resting-state EEG-derived features were utilized as input data to the proposed feature selection and classification method. The aim was to perform automatic classification of AUD patients and healthy controls. The validation of the proposed method involved real-EEG data acquired from 30 AUD patients and 30 age-matched healthy controls. The resting-state EEG-derived features such as synchronization likelihood (SL) were computed involving 19 scalp locations resulted into 513 features. Furthermore, the features were rank-ordered to select the most discriminant features involving a rank-based feature selection method according to a criterion, i.e., receiver operating characteristics (ROC). Consequently, a reduced set of most discriminant features was identified and utilized further during classification of AUD patients and healthy controls. In this study, three different classification models such as Support Vector Machine (SVM), Naïve Bayesian (NB), and Logistic Regression (LR) were used.

    RESULTS: The study resulted into SVM classification accuracy=98%, sensitivity=99.9%, specificity=95%, and f-measure=0.97; LR classification accuracy=91.7%, sensitivity=86.66%, specificity=96.6%, and f-measure=0.90; NB classification accuracy=93.6%, sensitivity=100%, specificity=87.9%, and f-measure=0.95.

    CONCLUSION: The SL features could be utilized as objective markers to screen the AUD patients and healthy controls.

  20. Amin HU, Mumtaz W, Subhani AR, Saad MNM, Malik AS
    Front Comput Neurosci, 2017;11:103.
    PMID: 29209190 DOI: 10.3389/fncom.2017.00103
    Feature extraction is an important step in the process of electroencephalogram (EEG) signal classification. The authors propose a "pattern recognition" approach that discriminates EEG signals recorded during different cognitive conditions. Wavelet based feature extraction such as, multi-resolution decompositions into detailed and approximate coefficients as well as relative wavelet energy were computed. Extracted relative wavelet energy features were normalized to zero mean and unit variance and then optimized using Fisher's discriminant ratio (FDR) and principal component analysis (PCA). A high density EEG dataset validated the proposed method (128-channels) by identifying two classifications: (1) EEG signals recorded during complex cognitive tasks using Raven's Advance Progressive Metric (RAPM) test; (2) EEG signals recorded during a baseline task (eyes open). Classifiers such as, K-nearest neighbors (KNN), Support Vector Machine (SVM), Multi-layer Perceptron (MLP), and Naïve Bayes (NB) were then employed. Outcomes yielded 99.11% accuracy via SVM classifier for coefficient approximations (A5) of low frequencies ranging from 0 to 3.90 Hz. Accuracy rates for detailed coefficients were 98.57 and 98.39% for SVM and KNN, respectively; and for detailed coefficients (D5) deriving from the sub-band range (3.90-7.81 Hz). Accuracy rates for MLP and NB classifiers were comparable at 97.11-89.63% and 91.60-81.07% for A5 and D5 coefficients, respectively. In addition, the proposed approach was also applied on public dataset for classification of two cognitive tasks and achieved comparable classification results, i.e., 93.33% accuracy with KNN. The proposed scheme yielded significantly higher classification performances using machine learning classifiers compared to extant quantitative feature extraction. These results suggest the proposed feature extraction method reliably classifies EEG signals recorded during cognitive tasks with a higher degree of accuracy.
Filters
Contact Us

Please provide feedback to Administrator (afdal@afpm.org.my)

External Links