Displaying publications 141 - 160 of 437 in total

Abstract:
Sort:
  1. Hairi NN, Bulgiba A, Cumming RG, Naganathan V, Mudla I
    J Am Geriatr Soc, 2011 Mar;59(3):557-9.
    PMID: 21391950 DOI: 10.1111/j.1532-5415.2010.03301.x
    Matched MeSH terms: Regression Analysis
  2. Hamdi OA, Anouar el H, Shilpi JA, Trabolsy ZB, Zain SB, Zakaria NS, et al.
    Int J Mol Sci, 2015 Apr 27;16(5):9450-68.
    PMID: 25923077 DOI: 10.3390/ijms16059450
    A series of 21 compounds isolated from Curcuma zedoaria was subjected to cytotoxicity test against MCF7; Ca Ski; PC3 and HT-29 cancer cell lines; and a normal HUVEC cell line. To rationalize the structure-activity relationships of the isolated compounds; a set of electronic; steric and hydrophobic descriptors were calculated using density functional theory (DFT) method. Statistical analyses were carried out using simple and multiple linear regressions (SLR; MLR); principal component analysis (PCA); and hierarchical cluster analysis (HCA). SLR analyses showed that the cytotoxicity of the isolated compounds against a given cell line depend on certain descriptors; and the corresponding correlation coefficients (R2) vary from 0%-55%. MLR results revealed that the best models can be achieved with a limited number of specific descriptors applicable for compounds having a similar basic skeleton. Based on PCA; HCA and MLR analyses; active compounds were classified into subgroups; which was in agreement with the cell based cytotoxicity assay.
    Matched MeSH terms: Regression Analysis
  3. Hameed BH, Tan IA, Ahmad AL
    J Hazard Mater, 2008 Oct 30;158(2-3):324-32.
    PMID: 18329169 DOI: 10.1016/j.jhazmat.2008.01.088
    Oil palm fibre was used to prepare activated carbon using physiochemical activation method which consisted of potassium hydroxide (KOH) treatment and carbon dioxide (CO(2)) gasification. The effects of three preparation variables: the activation temperature, activation time and chemical impregnation (KOH:char) ratio on methylene blue (MB) uptake from aqueous solutions and activated carbon yield were investigated. Based on the central composite design (CCD), a quadratic model and a two factor interaction (2FI) model were respectively developed to correlate the preparation variables to the MB uptake and carbon yield. From the analysis of variance (ANOVA), the significant factors on each experimental design response were identified. The optimum activated carbon prepared from oil palm fibre was obtained by using activation temperature of 862 degrees C, activation time of 1h and chemical impregnation ratio of 3.1. The optimum activated carbon showed MB uptake of 203.83 mg/g and activated carbon yield of 16.50%. The equilibrium data for adsorption of MB on the optimum activated carbon were well represented by the Langmuir isotherm, giving maximum monolayer adsorption capacity as high as 400mg/g at 30 degrees C.
    Matched MeSH terms: Regression Analysis
  4. Hamid TA, Dzaher A, Ching SM
    Med J Malaysia, 2019 Jun;74(3):198-204.
    PMID: 31256173
    BACKGROUND: Research has found that social network, social support and religiosity are associated with depression in elderly people. However, these predictors of depression have not been fully explored among the high risk elderly population. This study aims to examine the prevalence and factors associated with depression among Malaysian elderly subjects who had experienced major life events.

    METHODS: This is a cross-section study of a subsample of 594 participants from the original sample of 2322 Malaysian elderly respondents, who had experienced major life events. Information on socio-demographic, social network, social support, religiosity and depression were collected through an interviewer-administered questionnaire. A multiple linear regression analysis was used to determine the factors associated with depression among elderly who experienced major life events.

    RESULTS: Overall prevalence of depression among subsample of Malaysian elderly facing major life events was 9.4%. The results showed that age (p≤0.01), income (p≤0.001) and social network (p≤0.05) were significant associated with depression. In other words, with increasing age, low income as well as small social network associated with high risk of developing depression among elderly who had experienced major life events CONCLUSION: Other than age and income, social network were also associated with depression among elderly respondents who had experienced major life events. Therefore, professionals who are working with elderly with major life events should seek ways to enhance elderly networking as one of the strategies to prevent depression.

    Matched MeSH terms: Regression Analysis
  5. Haque S, Khamis MF, Alam MK, Ahmad WMAW
    J Craniofac Surg, 2020 May 04.
    PMID: 32371703 DOI: 10.1097/SCS.0000000000006464
    Studies have claimed that the maxillary arch dimension of unilateral cleft lip and palate (UCLP) patient is significantly smaller than normal patient. Multiple factors (both congenital and post natal treatment factors) are believed to have an impact on the treatment outcome (maxillary arch retardation) of UCLP patient. The aim of this study was to evaluate the effects of multiple factors on the treatment outcome by assessing the maxillary arch dimension of UCLP Children. Eighty-five Malaysian UCLP children were taken who received cheiloplasty and palatoplasty. Laser scanned 3D digital models of UCLP subjects were prepared before any orthodontic treatment and bone grafting at 7.69 ± 2.46 (mean± SD) years of age. Intercanine width (ICW), intermolar width (IMW), and arch depth (AD) measurements of maxillary arch were measured with Mimics software. Multiple linear regression analyses were used to evaluate the association between multiple factors (gender, UCLP type, UCLP side, family history of cleft, family history of class III malocclusion, techniques of cheiloplasty, and techniques of palatoplasty) and maxillary arch dimensions (ICW, IMW, and AD). P value was set at 5%. Significant association was found between 2 techniques of cheiloplasty and ICW (P = 0.001) and also between 2 techniques of palatoplasty and ICW (P = 0.046) of maxilla. No significant association observed in IMW and AD in relation to all other factors. Modified Millard techniques of Cheiloplasty and Bardach technique of palatoplasty had unfavorable effect on the treatment outcome by assessing the maxillary arch dimension (ICW) using laser scanned 3D digital models in Malaysian UCLP children.
    Matched MeSH terms: Regression Analysis
  6. Harun MA, Safari MJS, Gul E, Ab Ghani A
    Environ Sci Pollut Res Int, 2021 Oct;28(38):53097-53115.
    PMID: 34023993 DOI: 10.1007/s11356-021-14479-0
    The investigation of sediment transport in tropical rivers is essential for planning effective integrated river basin management to predict the changes in rivers. The characteristics of rivers and sediment in the tropical region are different compared to those of the rivers in Europe and the USA, where the median sediment size tends to be much more refined. The origins of the rivers are mainly tropical forests. Due to the complexity of determining sediment transport, many sediment transport equations were recommended in the literature. However, the accuracy of the prediction results remains low, particularly for the tropical rivers. The majority of the existing equations were developed using multiple non-linear regression (MNLR). Machine learning has recently been the method of choice to increase model prediction accuracy in complex hydrological problems. Compared to the conventional MNLR method, machine learning algorithms have advanced and can produce a useful prediction model. In this research, three machine learning models, namely evolutionary polynomial regression (EPR), multi-gene genetic programming (MGGP) and M5 tree model (M5P), were implemented to model sediment transport for rivers in Malaysia. The formulated variables for the prediction model were originated from the revised equations reported in the relevant literature for Malaysian rivers. Among the three machine learning models, in terms of different statistical measurement criteria, EPR gives the best prediction model, followed by MGGP and M5P. Machine learning is excellent at improving the prediction distribution of high data values but lacks accuracy compared to observations of lower data values. These results indicate that further study needs to be done to improve the machine learning model's accuracy to predict sediment transport.
    Matched MeSH terms: Regression Analysis
  7. Hashim JH, Hashim Z, Omar A, Shamsudin SB
    Asia Pac J Public Health, 2000;12(2):65-70.
    PMID: 11836921
    The objective of this article is to study the influence of exposure and socio-economic variables on the blood lead level of Malaysian school children. Data on respirable lead and blood lead of 346 school children were obtained from Kuala Lumpur (urban), Kemaman (semi-urban) and Setiu (rural). Respirable lead and blood lead were highest for Kuala Lumpur (95 ng/m3 and 5.26 micrograms/dL) followed by Kemaman (27 ng/m3 and 2.81 micrograms/dL) and Setiu (15 ng/m3 and 2.49 micrograms/dL), and the differences were statistically significant. The percentage of school children with excessive blood lead of 10 micrograms/dL or greater was 6.36% overall, and highest for Kuala Lumpur (11.73%). Regression analyses show that urban children are at higher risk of exhibiting excessive blood lead levels. Kuala Lumpur's school children have a 25 times greater risk of having excessive blood lead levels when compared to Kemaman's and Setiu's school children. Respirable and blood lead were correlated (r = 0.999, p = 0.021). Urban school children acquire higher blood lead levels than their rural and semi-urban counterparts, even after controlling for age, sex, parents' education and income levels. In conclusion, it is time that lead in the Malaysian environment and population be monitored closely, especially its temporal and spatial variability. Only then can a comprehensive preventive strategy be implemented.
    Matched MeSH terms: Regression Analysis
  8. Hassan MR, Suan MA, Soelar SA, Mohammed NS, Ismail I, Ahmad F
    Asian Pac J Cancer Prev, 2016;17(7):3575-81.
    PMID: 27510011
    BACKGROUND: Cancer survival analysis is an essential indicator for effective early detection and improvements in cancer treatment. This study was undertaken to document colorectal cancer survival and associated prognostic factors in Malaysians.

    MATERIALS AND METHODS: All data were retrieved from the National Cancer Patient Registry Colorectal Cancer. Only cases with confirmed diagnosis through histology between the year 2008 and 2009 were included. Retrieved data include sociodemographic information, pathological features and treatment received. Survival curves were plotted using the KaplanMeier method. Univariate analysis of all variables was then made using the Logrank test. All significant factors that influenced survival of patients were further analysed in a multivariate analysis using Cox' regression.

    RESULTS: Total of 1,214 patients were included in the study. The overall 3 and 5year survival rates were 59.1% and 48.7%, respectively. Patients with localized tumours had better prognosis compared to those with advanced stage cancer. In univariate analysis, staging at diagnosis (p<0.001), primary tumour size (p<0.001), involvement of lymph nodes (p<0.001) and treatment modalities (p=0.001) were found to be predictors of survival. None of the sociodemographic characteristics were found to exert any influence. In Cox regression analysis, staging at diagnosis (p<0.001), primary tumour size (p<0.001), involvement of lymph nodes (p<0.001) and treatment modalities (p<0.001) were determined as independent prognostic factors of survival after adjusted for age, gender and ethnicity.

    CONCLUSIONS: The overall survival rate for colorectal cancer patients in Malaysia is similar to those in other Asian countries, with staging at diagnosis, primary tumor size, involvement of lymph node and treatment modalities having significant effects. More efforts are needed to improve national survival rates in future.
    Matched MeSH terms: Regression Analysis
  9. Hazura, H., Wan Norhaida, W.A., Zahiruddin, O., Ruzita, J.
    MyJurnal
    Introduction: A number of researches suggest smoking serves as a form of self-medication to reduce the side effects of antipsychotic medications, to alleviate negative symptoms, and/or to ameliorate a number of cognitive deficits associated with schizophrenia. Objective: The aim of this study was to investigate the association of cigarette smoking with verbal working memory and psychopathology of patients with schizophrenia. Methods: Fifty-three patients with schizophrenia were assessed by a single rater using the Malay Version of Auditory Verbal Learning Test (MVAVLT) and Positive and Negative Syndrome Scale (PANSS). Smokers (n=30) were compared with nonsmokers (n=23) on socio-demographic, clinical, psychopathology and verbal memory variables. Single linear and multiple regression analysis were performed to determine factors associated with verbal memory performance.
    Results: Verbal working memory performance is associated with lower number of admission to ward, lesser severity of the negative symptoms or general psychopathology of schizophrenia and use of atypical antipsychotics in all schizophrenic subjects. Smokers with schizophrenia scored higher than non- smoker in measures that reflect immediate memory, delayed recall and recognition memory. However, the association between verbal working
    memory performance and smoking status was found to be not significant. Conclusion: Verbal working memory performance is associated with negative symptoms but not positive symptoms. This study failed to detect association of smoking on verbal working memory.
    Matched MeSH terms: Regression Analysis
  10. Hearn AJ, Cushman SA, Ross J, Goossens B, Hunter LTB, Macdonald DW
    PLoS One, 2018;13(7):e0200828.
    PMID: 30028844 DOI: 10.1371/journal.pone.0200828
    Niche differentiation, the partitioning of resources along one or more axes of a species' niche hyper-volume, is widely recognised as an important mechanism for sympatric species to reduce interspecific competition and predation risk, and thus facilitate co-existence. Resource partitioning may be facilitated by behavioural differentiation along three main niche dimensions: habitat, food and time. In this study, we investigate the extent to which these mechanisms can explain the coexistence of an assemblage of five sympatric felids in Borneo. Using multi-scale logistic regression, we show that Bornean felids exhibit differences in both their broad and fine-scale habitat use. We calculate temporal activity patterns and overlap between these species, and present evidence for temporal separation within this felid guild. Lastly, we conducted an all-subsets logistic regression to predict the occurrence of each felid species as a function of the co-occurrence of a large number of other species and showed that Bornean felids co-occurred with a range of other species, some of which could be candidate prey. Our study reveals apparent resource partitioning within the Bornean felid assemblage, operating along all three niche dimension axes. These results provide new insights into the ecology of these species and the broader community in which they live and also provide important information for conservation planning for this guild of predators.
    Matched MeSH terms: Regression Analysis
  11. Hemmati A, Mirghaed SR, Rahmani F, Komasi S
    Malays J Med Sci, 2019 Sep;26(5):74-87.
    PMID: 31728120 DOI: 10.21315/mjms2019.26.5.7
    Background: The present study was conducted to determine the differential profile of social anxiety disorder (SAD) and avoidant personality disorder (APD) based on dimensional diagnosis in criterion B of the DSM-5 Alternative Model for Personality Disorders (DSM-5-AMPD) in a college sample.

    Methods: Samples of this cross-sectional study included 320 (23.08 ± 2.66 years; 57% female) college students in western Iran during February 2015 to December 2017. Liebowitz-social anxiety scale, PID-5, SCID-II, SCID-II-SQ and diagnostic interview for SAD were the tools. The data were analysed using Pearson correlation and multiple linear regression analysis.

    Results: Forty-three and 38 participants met criteria for SAD alone and APD, respectively. Five main domains of PID-5 could explain 29% and 54% of the variance of SAD and APD, respectively. Facets of negative affect, detachment, antagonism, disinhibition, and psychoticism could explain 25% versus 43%, 26% versus 54%, 7% versus 27%, 21% versus 41%, 13% versus 30% of the variance of SAD and APD, respectively.

    Conclusion: SAD and APD probably refer to two distinct mental states having prominent anxiety, emotional instability, and interpersonal pattern of avoidance and detachment of challenge. SAD is a simple form of mental disturbances with anxiety in its core features; although, APD is possibly referring to more complicated psychopathology.

    Matched MeSH terms: Regression Analysis
  12. Hie, Ung Ngian, Jamsiah, M., Syed Mohamed Aljunid, Sharifa Ezat, W.P.
    MyJurnal
    This study examines the level of quality initiatives commitment among public hospital managers and its determinants in view of limited study :0 date and a decline in self-initiated quality initiatives activities in Sarawak, Malaysia. This is a cross-sectional study with universal sampling method conducted in all the Z1 public iwspimls in Sarawak. The study population were the senior, middle and lower level managers. The research wal was self-administered structured questionnaire. A total of 382 managers responded, corresponding ta a response irate of 8 7. 2%. As a complement, four focus group discussions were conducted, consisting 31 participants. It was found that the level of quality initiatives commitment 0f managers was generally high (mecm= 4.23, SD=O.45). The regression analysis indicated that empowerment, communication and procedural justice (promotion) accounted for 38.9%, 346% and 1.2% respectively of the variation in commitment level. Dissatisfaction with resources, top management commitment and peer influence are among others being identified by participants of focus groups as important determinants of quality initiatives commitment. It is strongly recommended that there should be greater empowerment of hospital managers, more structured and effective communication, greater transparency in procedure for promotion and commitment of resources to quality efforts.
    Matched MeSH terms: Regression Analysis
  13. Hin LY, Khairuddin Y, Ng KB
    Asia Oceania J Obstet Gynaecol, 1994 Dec;20(4):389-94.
    PMID: 7832671
    We reviewed the deliveries in a teaching hospital in a multiracial community over the period of one year (1988), and investigated the relationship between maternal height, ethnic origin, and the extremes of birth weight with the likelihood of emergency lower segment caesarean section (LSCS). After excluding patients with obvious indications for LSCS, 5,050 patients were entered in the study. Chi-square analysis showed that the risk of emergency LSCS is significantly higher in the Indians compared to Chinese and Malays, but does not differ significantly between the latter two groups. Logistic regression analysis showed that birth weight of less than 2,500 g or greater than 3,500 g is the most significant association with emergency LSCS rate. Conditional logistic regression showed that, provided the individuals conformed to the characteristics of the cohort in this study, risk of emergency LSCS for a 150 cm (25th centile) tall Indian pregnant lady is almost twice that of a 158 cm (75th centile) tall non-Indian).
    Matched MeSH terms: Regression Analysis
  14. Hooi LN
    Med J Malaysia, 2003 Oct;58(4):506-15.
    PMID: 15190625
    A study was conducted to determine the clinical factors that affect the quality of life in adult asthmatics. As part of their routine follow-up visit, 399 patients completed the SF-36 quality of life questionnaire, had peak expiratory flow rate readings (PEFR) taken and were interviewed to determine current symptom severity. The grade of severity of asthma was verified by the consultant physician in-charge. The mean age of the patients was 41.8 years and 31.8% of the patients were men. Most of the patients were Malay (64.7%), 89% had at least secondary level education and the mean duration of asthma was 17.6 years. The majority of patients had moderate or severe disease (43.6% and 55.9% respectively). For asthmatics with moderate or severe symptoms of chest tightness and/or shortness of breath, all domains of SF-36 scored significantly lower than those with mild symptoms, with the exception of the domain bodily pain. Patients with moderate/severe cough recorded significantly lower scores than those with mild cough for all domains except for bodily pain and social functioning. Only the physical functioning, role physical, general health and role emotional scores were significantly worse in those with a consultant grade of severe asthma compared to those with mild/moderate asthma. Patients with PEFR < 80% predicted had lower scores for the domains physical functioning, role physical and general health than those with PEFR > or = 80% predicted, but the scores for the other domains were similar in both groups. Quality of life is significantly impaired in adult asthmatics with current respiratory symptoms. However, consultant grade of severity of asthma and PEFR readings do not affect quality of life scores as much.
    Study site: Asthma clinics, hospitals, Malaysia
    Matched MeSH terms: Regression Analysis
  15. Hossain MG, Zyroul R, Pereira BP, Kamarul T
    J Hand Surg Eur Vol, 2012 Jan;37(1):65-70.
    PMID: 21816889 DOI: 10.1177/1753193411414639
    Grip strength is an important measure used to monitor the progression of a condition, and to evaluate outcomes of treatment. We assessed how various physical and social factors predict normal grip strength in an adult Malaysian population of mixed Asian ethnicity (254 men, 246 women). Grip strength was recorded using the Jamar dynamometer. The mean grip strength for the dominant hand was 29.8 kg for men and 17.6 kg for women. Multiple regression analysis demonstrated that the dominant hand grip strength was positively associated with height and body mass index, and negatively associated with age for both sexes. Dominant hand grip strength was related to work status for men (p 
    Matched MeSH terms: Regression Analysis
  16. Hossain MG, Saw A, Ohtsuki F, Lestrel PE, Kamarul T
    Singapore Med J, 2011 Nov;52(11):818-23.
    PMID: 22173252
    Secular changes in the head and body dimensions of the Japanese population were recorded during the last century, but studies on Japanese adult facial shape were poorly documented. This study aimed to document the secular changes in facial shape and their association with craniofacial measures of Japanese adult female students.
    Matched MeSH terms: Regression Analysis
  17. Hossain MG, Saw A, Alam R, Ohtsuki F, Kamarul T
    Singapore Med J, 2013 Sep;54(9):516-20.
    PMID: 24068061
    INTRODUCTION: Cephalic index (CI), the ratio of head breadth to head length, is widely used to categorise human populations. The aim of this study was to access the impact of anthropometric measurements on the CI of male Japanese university students.

    METHODS: This study included 1,215 male university students from Tokyo and Kyoto, selected using convenient sampling. Multiple regression analysis was used to determine the effect of anthropometric measurements on CI.

    RESULTS: The variance inflation factor (VIF) showed no evidence of a multicollinearity problem among independent variables. The coefficients of the regression line demonstrated a significant positive relationship between CI and minimum frontal breadth (p < 0.01), bizygomatic breadth (p < 0.01) and head height (p < 0.05), and a negative relationship between CI and morphological facial height (p < 0.01) and head circumference (p < 0.01). Moreover, the coefficient and odds ratio of logistic regression analysis showed a greater likelihood for minimum frontal breadth (p < 0.01) and bizygomatic breadth (p < 0.01) to predict round-headedness, and morphological facial height (p < 0.05) and head circumference (p < 0.01) to predict long-headedness. Stepwise regression analysis revealed bizygomatic breadth, head circumference, minimum frontal breadth, head height and morphological facial height to be the best predictor craniofacial measurements with respect to CI.

    CONCLUSION: The results suggest that most of the variables considered in this study appear to influence the CI of adult male Japanese students.
    Matched MeSH terms: Regression Analysis
  18. Hossain MZ, Daud S, Nambiar P, Razak FA, Ab-Murat N, Saub R, et al.
    Arch Oral Biol, 2017 Aug;80:51-55.
    PMID: 28371626 DOI: 10.1016/j.archoralbio.2017.03.018
    OBJECTIVE: The aim of this study was to investigate correlations between dental pulp cell count of odontoblasts, subodontoblasts and fibroblasts and age, within different age groups. Formulation of regression equations using the dental pulp cell count for predicting age was attempted.

    DESIGN: Eighty-one extracted teeth were grouped into two age groups (6-25 years, 26-80 years). The teeth were demineralized and histological sections were prepared for cell count. Regression equations were generated from regression analysis of cell count and tested for age estimation.

    RESULTS: The number of dental pulp cells were found to increase until around the third decade of life and following this, the odontoblasts and subodontoblasts cell numbers began to decline while the fibroblasts seemed to remain almost stationary. The Pearson correlation test revealed a significant positive correlation between the cell number for all type of cells and age in the 6-25 years group (r=+0.791 for odontoblasts, r=+0.600 for subodontoblasts and r=+0.680 for fibroblasts). In the 26-80 years age group, a significant negative correlation of the odontoblasts (r=-0.777) and subodontoblasts (r=-0.715) with age was observed but for fibroblasts, the correlation value was negligible (r=-0.165). Regression equations generated using odontoblasts and subodontoblasts cell number were applicable for age estimation. The standard error of estimates (SEEs) were around±5years for 6-25 years and±8years for 26-80 years age groups. The mean values of the estimated and chronological ages were not significantly different.

    CONCLUSIONS: A significant correlation between the cell count of odontoblasts and subodontoblasts with age was demonstrated. Regression equations using odontoblasts and subodontoblasts cell number can be used to predict age with some limitations.

    Matched MeSH terms: Regression Analysis
  19. Hu J, Neoh KB, Appel AG, Lee CY
    PMID: 22085890 DOI: 10.1016/j.cbpa.2011.10.028
    The foraging patterns of termites are strongly related to physiological limits in overcoming desiccation stress. In this study, we examined moisture preferences and physiological characteristics of Macrotermes carbonarius (Hagen) and M. gilvus (Hagen) as both exhibit conspicuous patterns of foraging activity. Despite both species showing no significant differences in calculated cuticular permeability, and percentage of total body water, they differed greatly in rate of water loss and surface area to volume ratio. For example, M. carbonarius which had a lower surface area to volume ratio (29.26-53.66) showed lower rate of water loss and percentage of total body water loss. This also resulted in higher LT(50) when exposed to extreme conditions (≈2% RH). However, contrasting observations were made in M. gilvus that has smaller size with higher surface area to volume ratio of 40.28-69.75. It is likely that the standard equation for calculating insect surface areas is inadequate for these termite species. The trend was further supported by the result of a moisture preference bioassay that indicated M. carbonarius had a broader range of moisture preference (between 5% and 20%) than M. gilvus which had a relatively narrow moisture preference (only 20%). These results explain why M. carbonarius can tolerate desiccation stress for a longer period foraging above-ground in the open air; while M. gilvus only forages below ground or concealed within foraging mud tubes.
    Matched MeSH terms: Regression Analysis
  20. Huan NJ, Palaniappan R
    J Neural Eng, 2004 Sep;1(3):142-50.
    PMID: 15876633
    In this paper, we have designed a two-state brain-computer interface (BCI) using neural network (NN) classification of autoregressive (AR) features from electroencephalogram (EEG) signals extracted during mental tasks. The main purpose of the study is to use Keirn and Aunon's data to investigate the performance of different mental task combinations and different AR features for BCI design for individual subjects. In the experimental study, EEG signals from five mental tasks were recorded from four subjects. Different combinations of two mental tasks were studied for each subject. Six different feature extraction methods were used to extract the features from the EEG signals: AR coefficients computed with Burg's algorithm, AR coefficients computed with a least-squares (LS) algorithm and adaptive autoregressive (AAR) coefficients computed with a least-mean-square (LMS) algorithm. All the methods used order six applied to 125 data points and these three methods were repeated with the same data but with segmentation into five segments in increments of 25 data points. The multilayer perceptron NN trained by the back-propagation algorithm (MLP-BP) and linear discriminant analysis (LDA) were used to classify the computed features into different categories that represent the mental tasks. We compared the classification performances among the six different feature extraction methods. The results showed that sixth-order AR coefficients with the LS algorithm without segmentation gave the best performance (93.10%) using MLP-BP and (97.00%) using LDA. The results also showed that the segmentation and AAR methods are not suitable for this set of EEG signals. We conclude that, for different subjects, the best mental task combinations are different and proper selection of mental tasks and feature extraction methods are essential for the BCI design.
    Matched MeSH terms: Regression Analysis
Filters
Contact Us

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

External Links