Displaying publications 1 - 20 of 252 in total

Abstract:
Sort:
  1. Yusoff, A.N., Mohamad, M., Hamid, K.A., Hamid, A.I.A., Manan, H.A., Hashim, M.H.
    ASM Science Journal, 2010;4(2):158-172.
    MyJurnal
    In this multiple-subject study, intrinsic couplings between the primary motor (M1) and supplementary motor areas (SMA) were investigated. Unilateral (UNIright and UNIleft) self-paced tapping of hand fingers were performed to activate M1 and SMA. The intrinsic couplings were analysed using statistical parametric mapping, dynamic causal modeling (DCM) and Bayesian model analysis. Brain activation observed for UNIright and UNIleft showed contralateral and ipsilateral involvement of M1 and SMA. Ten full connectivity models were constructed with right and left M1 and SMA as processing centres. DCM indicated that all subjects prefer M1 as the intrinsic input for UNIright and UNIleft as indicated by a large group Bayes factor (GBF). Positive evidence ratio (PER) that showed strong evidence of Model 3 and Model 6 against other models in at least 12 out of 16 subjects, supported GBF results. The GBF and PER results were later found to be consistent with that of BMS for group studies with high expected posterior probability and exceedance probability. It was concluded that during unilateral finger tapping, the contralateral M1 would act as the input centre which in turn triggered the propagation of signals to SMA in the same hemisphere and to M1 and SMA in the opposite hemisphere.
    Matched MeSH terms: Bayes Theorem
  2. Hosseinpour M, Sahebi S, Zamzuri ZH, Yahaya AS, Ismail N
    Accid Anal Prev, 2018 Sep;118:277-288.
    PMID: 29861069 DOI: 10.1016/j.aap.2018.05.003
    According to crash configuration and pre-crash conditions, traffic crashes are classified into different collision types. Based on the literature, multi-vehicle crashes, such as head-on, rear-end, and angle crashes, are more frequent than single-vehicle crashes, and most often result in serious consequences. From a methodological point of view, the majority of prior studies focused on multivehicle collisions have employed univariate count models to estimate crash counts separately by collision type. However, univariate models fail to account for correlations which may exist between different collision types. Among others, multivariate Poisson lognormal (MVPLN) model with spatial correlation is a promising multivariate specification because it not only allows for unobserved heterogeneity (extra-Poisson variation) and dependencies between collision types, but also spatial correlation between adjacent sites. However, the MVPLN spatial model has rarely been applied in previous research for simultaneously modelling crash counts by collision type. Therefore, this study aims at utilizing a MVPLN spatial model to estimate crash counts for four different multi-vehicle collision types, including head-on, rear-end, angle, and sideswipe collisions. To investigate the performance of the MVPLN spatial model, a two-stage model and a univariate Poisson lognormal model (UNPLN) spatial model were also developed in this study. Detailed information on roadway characteristics, traffic volume, and crash history were collected on 407 homogeneous segments from Malaysian federal roads. The results indicate that the MVPLN spatial model outperforms the other comparing models in terms of goodness-of-fit measures. The results also show that the inclusion of spatial heterogeneity in the multivariate model significantly improves the model fit, as indicated by the Deviance Information Criterion (DIC). The correlation between crash types is high and positive, implying that the occurrence of a specific collision type is highly associated with the occurrence of other crash types on the same road segment. These results support the utilization of the MVPLN spatial model when predicting crash counts by collision manner. In terms of contributing factors, the results show that distinct crash types are attributed to different subsets of explanatory variables.
    Matched MeSH terms: Bayes Theorem
  3. Khoo HL, Ahmed M
    Accid Anal Prev, 2018 Apr;113:106-116.
    PMID: 29407657 DOI: 10.1016/j.aap.2018.01.025
    This study had developed a passenger safety perception model specifically for buses taking into consideration the various factors, namely driver characteristics, environmental conditions, and bus characteristics using Bayesian Network. The behaviour of bus driver is observed through the bus motion profile, measured in longitudinal, lateral, and vertical accelerations. The road geometry is recorded using GPS and is computed with the aid of the Google map while the perceived bus safety is rated by the passengers in the bus in real time. A total of 13 variables were derived and used in the model development. The developed Bayesian Network model shows that the type of bus and the experience of the driver on the investigated route could have an influence on passenger's perception of their safety on buses. Road geometry is an indirect influencing factor through the driver's behavior. The findings of this model are useful for the authorities to structure an effective strategy to improve the level of perceived bus safety. A high level of bus safety will definitely boost passenger usage confidence which will subsequently increase ridership.
    Matched MeSH terms: Bayes Theorem
  4. de Vries B, Narayan R, McGeechan K, Santiagu S, Vairavan R, Burke M, et al.
    Acta Obstet Gynecol Scand, 2018 Jun;97(6):668-676.
    PMID: 29450884 DOI: 10.1111/aogs.13310
    INTRODUCTION: Cesarean section rates continue to increase globally. Prediction of intrapartum cesarean section could lead to preventive measures. Our aim was to assess the association between sonographically measured cervical length at 37 weeks of gestation and cesarean section among women planning a vaginal birth. The population was women with a low-risk pregnancy or with gestational diabetes.

    MATERIAL AND METHODS: This was a prospective cohort study conducted in a tertiary referral hospital in Sydney, Australia. In all, 212 women with a low-risk pregnancy or with gestational diabetes were recruited including 158 nulliparous and 54 parous women. Maternal demographic, clinical and ultrasound characteristics were collected at 37 weeks of gestation. Semi-Bayesian logistic regression and Markov chain Monte Carlo simulation were used to assess the relation between cervical length and cesarean section in labor.

    RESULTS: Rates of cesarean section were 5% (2/55) for cervical length ≤20 mm, 17% (17/101) for cervical length 20-32 mm, and 27% (13/56) for cervical length >32 mm. These rates were 4, 22 and 33%, respectively, in nulliparous women. In the semi-Bayesian analysis, the odds ratio for cesarean section was 6.2 (95% confidence interval 2.2-43) for cervical length 20-32 mm and 10 (95% confidence interval 4.8-74) for cervical length >32 mm compared with the lowest quartile of cervical length, after adjusting for maternal age, parity, height, prepregnancy body mass index, gestational diabetes, induction of labor, neonatal sex and birthweight centile.

    CONCLUSIONS: Cervical length at 37 weeks of gestation is associated with intrapartum cesarean section.

    Matched MeSH terms: Bayes Theorem
  5. Zakaria MN, Nik Othman NA, Musa Z
    Acta Otolaryngol, 2021 Nov;141(11):984-988.
    PMID: 34669557 DOI: 10.1080/00016489.2021.1990996
    BACKGROUND: The non-invasive tympanic electrocochleography (TM-ECochG) is useful for clinical diagnoses. Nevertheless, the influence of the electrode location on tympanic membrane (TM) on ECochG results needs to be studied.

    OBJECTIVE: The aim of the present study was to compare the TM-ECochG results obtained when the electrode was placed on the superior region versus the inferior region of TM.

    MATERIALS AND METHODS: Forty healthy adults (aged 29 to 50 years) participated in this comparative study. The TM-ECochG testing was conducted with the electrode placed on the superior and inferior regions of TM.

    RESULTS: SP and AP amplitudes were statistically higher for the inferior region of TM (p < .05). In contrast, SP/AP ratios were comparable between the two regions of TM (p = .417).

    CONCLUSIONS AND SIGNIFICANCE: In TM-ECochG recording, when the electrode was placed on the inferior region of TM, SP and AP amplitudes were greater than when the electrode was placed on the superior region of TM. On the other hand, SP/AP amplitude ratio was not affected by the location of electrode on TM. The findings from the present study could be useful to guide clinicians in optimizing TM-ECochG recording when testing their respective patients.

    Matched MeSH terms: Bayes Theorem
  6. Komahan K, Reidpath DD
    Am J Epidemiol, 2014 Aug 1;180(3):325-9.
    PMID: 24944286 DOI: 10.1093/aje/kwu129
    Correct identification of ethnicity is central to many epidemiologic analyses. Unfortunately, ethnicity data are often missing. Successful classification typically relies on large databases (n > 500,000 names) of known name-ethnicity associations. We propose an alternative naïve Bayesian strategy that uses substrings of full names. Name and ethnicity data for Malays, Indians, and Chinese were provided by a health and demographic surveillance site operating in Malaysia from 2011-2013. The data comprised a training data set (n = 10,104) and a test data set (n = 9,992). Names were spliced into contiguous 3-letter substrings, and these were used as the basis for the Bayesian analysis. Performance was evaluated on both data sets using Cohen's κ and measures of sensitivity and specificity. There was little difference between the classification performance in the training and test data (κ = 0.93 and 0.94, respectively). For the test data, the sensitivity values for the Malay, Indian, and Chinese names were 0.997, 0.855, and 0.932, respectively, and the specificity values were 0.907, 0.998, and 0.997, respectively. A naïve Bayesian strategy for the classification of ethnicity is promising. It performs at least as well as more sophisticated approaches. The possible application to smaller data sets is particularly appealing. Further research examining other substring lengths and other ethnic groups is warranted.
    Matched MeSH terms: Bayes Theorem*
  7. Matsuda I, Kubo T, Tuuga A, Higashi S
    Am. J. Phys. Anthropol., 2010 Jun;142(2):235-45.
    PMID: 20091847 DOI: 10.1002/ajpa.21218
    To understand the effects of environmental factors on a social system with multilevel society in proboscis monkey units, the temporal change of the local density of sleeping sites of monkeys was investigated along the Menanggul river from May 2005 to 2006 in Malaysia. Proboscis monkeys typically return to riverside trees for night sleeping. The sleeping site locations of a one-male unit (BE-unit) were recorded and the locations of other one-male and all-male units within 500 m of the BE-unit were verified. In addition, environmental factors (food availability, the water level of the river, and the river width) and copulation frequency of BE-unit were recorded. From the analyses of the distance from the BE-unit to the nearest neighbor unit, no spatial clumping of the sleeping sites of monkey units on a smaller scale was detected. The results of a Bayesian analysis suggest that the conditional local density around the BE-unit can be predicted by the spatial heterogeneity along the river and by the temporal change of food availability, that is, the local density of monkey units might increase due to better sleeping sites with regard to predator attacks and clumped food sources; proboscis monkeys might not exhibit high-level social organization previously reported. In addition, this study shows the importance of data analysis that considers the effects of temporal autocorrelation, because the daily measurements of longitudinal data on monkeys are not independent of each other.
    Matched MeSH terms: Bayes Theorem
  8. Tamrin NAM, Zainudin R, Esa Y, Alias H, Isa MNM, Croft L, et al.
    Animals (Basel), 2020 Dec 10;10(12).
    PMID: 33321745 DOI: 10.3390/ani10122359
    Taste perception is an essential function that provides valuable dietary and sensory information, which is crucial for the survival of animals. Studies into the evolution of the sweet taste receptor gene (TAS1R2) are scarce, especially for Bornean endemic primates such as Nasalis larvatus (proboscis monkey), Pongo pygmaeus (Bornean orangutan), and Hylobates muelleri (Muller's Bornean gibbon). Primates are the perfect taxa to study as they are diverse dietary feeders, comprising specialist folivores, frugivores, gummivores, herbivores, and omnivores. We constructed phylogenetic trees of the TAS1R2 gene for 20 species of anthropoid primates using four different methods (neighbor-joining, maximum parsimony, maximum-likelihood, and Bayesian) and also established the time divergence of the phylogeny. The phylogeny successfully separated the primates into their taxonomic groups as well as by their dietary preferences. Of note, the reviewed time of divergence estimation for the primate speciation pattern in this study was more recent than the previously published estimates. It is believed that this difference may be due to environmental changes, such as food scarcity and climate change, during the late Miocene epoch, which forced primates to change their dietary preferences. These findings provide a starting point for further investigation.
    Matched MeSH terms: Bayes Theorem
  9. Ahmad Fadzil M, Ngah NF, George TM, Izhar LI, Nugroho H, Adi Nugroho H
    PMID: 21097305 DOI: 10.1109/IEMBS.2010.5628041
    Diabetic retinopathy (DR) is a sight threatening complication due to diabetes mellitus that affects the retina. At present, the classification of DR is based on the International Clinical Diabetic Retinopathy Disease Severity. In this paper, FAZ enlargement with DR progression is investigated to enable a new and an effective grading protocol DR severity in an observational clinical study. The performance of a computerised DR monitoring and grading system that digitally analyses colour fundus image to measure the enlargement of FAZ and grade DR is evaluated. The range of FAZ area is optimised to accurately determine DR severity stage and progression stages using a Gaussian Bayes classifier. The system achieves high accuracies of above 96%, sensitivities higher than 88% and specificities higher than 96%, in grading of DR severity. In particular, high sensitivity (100%), specificity (>98%) and accuracy (99%) values are obtained for No DR (normal) and Severe NPDR/PDR stages. The system performance indicates that the DR system is suitable for early detection of DR and for effective treatment of severe cases.
    Matched MeSH terms: Bayes Theorem
  10. Sulaiman R, Azeman NH, Abu Bakar MH, Ahmad Nazri NA, Masran AS, Ashrif A Bakar A
    Appl Spectrosc, 2023 Feb;77(2):210-219.
    PMID: 36348500 DOI: 10.1177/00037028221140924
    Nutrient solution plays an essential role in providing macronutrients to hydroponic plants. Determining nitrogen in the form of nitrate is crucial, as either a deficient or excessive supply of nitrate ions may reduce the plant yield or lead to environmental pollution. This work aims to evaluate the performance of feature reduction techniques and conventional machine learning (ML) algorithms in determining nitrate concentration levels. Two features reduction techniques, linear discriminant analysis (LDA) and principal component analysis (PCA), and seven ML algorithms, for example, k-nearest neighbors (KNN), support vector machine, decision trees, naïve bayes, random forest (RF), gradient boosting, and extreme gradient boosting, were evaluated using a high-dimensional spectroscopic dataset containing measured nitrate-nitrite mixed solution absorbance data. Despite the limited and uneven number of samples per class, this study demonstrated that PCA outperformed LDA on the high-dimensional spectroscopic dataset. The classification accuracy of ML algorithms combined with PCA ranged from 92.7% to 99.8%, whereas the classification accuracy of ML algorithms combined with LDA ranged from 80.7% to 87.6%. The PCA with the RF algorithm exhibited the best performance with 99.8% accuracy.
    Matched MeSH terms: Bayes Theorem
  11. Ng KT, Takebe Y, Kamarulzaman A, Tee KK
    Arch Virol, 2021 Jan;166(1):225-229.
    PMID: 33084935 DOI: 10.1007/s00705-020-04855-5
    Genome sequences of members of a potential fourth rhinovirus (RV) species, provisionally denoted as rhinovirus A clade D, from patients with acute respiratory infection were determined. Bayesian coalescent analysis estimated that clade D emerged around the 1940s and diverged further around 2006-2007 into two distinctive sublineages (RV-A8-like and RV-A45-like) that harbored unique "clade-defining" substitutions. Similarity plots and bootscan mapping revealed a recombination breakpoint located in the 5'-UTR region of members of the RV-A8-like sublineage. Phylogenetic reconstruction revealed the distribution of clade D viruses in the Asia Pacific region and in Europe, underlining its worldwide distribution.
    Matched MeSH terms: Bayes Theorem
  12. Lim CP, Harrison RF, Kennedy RL
    Artif Intell Med, 1997 Nov;11(3):215-39.
    PMID: 9413607
    This paper presents a study of the application of autonomously learning multiple neural network systems to medical pattern classification tasks. In our earlier work, a hybrid neural network architecture has been developed for on-line learning and probability estimation tasks. The network has been shown to be capable of asymptotically achieving the Bayes optimal classification rates, on-line, in a number of benchmark classification experiments. In the context of pattern classification, however, the concept of multiple classifier systems has been proposed to improve the performance of a single classifier. Thus, three decision combination algorithms have been implemented to produce a multiple neural network classifier system. Here the applicability of the system is assessed using patient records in two medical domains. The first task is the prognosis of patients admitted to coronary care units; whereas the second is the prediction of survival in trauma patients. The results are compared with those from logistic regression models, and implications of the system as a useful clinical diagnostic tool are discussed.
    Matched MeSH terms: Bayes Theorem
  13. 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.

    Matched MeSH terms: Bayes Theorem
  14. Low JZB, Khang TF, Tammi MT
    BMC Bioinformatics, 2017 12 28;18(Suppl 16):575.
    PMID: 29297307 DOI: 10.1186/s12859-017-1974-4
    BACKGROUND: In current statistical methods for calling differentially expressed genes in RNA-Seq experiments, the assumption is that an adjusted observed gene count represents an unknown true gene count. This adjustment usually consists of a normalization step to account for heterogeneous sample library sizes, and then the resulting normalized gene counts are used as input for parametric or non-parametric differential gene expression tests. A distribution of true gene counts, each with a different probability, can result in the same observed gene count. Importantly, sequencing coverage information is currently not explicitly incorporated into any of the statistical models used for RNA-Seq analysis.

    RESULTS: We developed a fast Bayesian method which uses the sequencing coverage information determined from the concentration of an RNA sample to estimate the posterior distribution of a true gene count. Our method has better or comparable performance compared to NOISeq and GFOLD, according to the results from simulations and experiments with real unreplicated data. We incorporated a previously unused sequencing coverage parameter into a procedure for differential gene expression analysis with RNA-Seq data.

    CONCLUSIONS: Our results suggest that our method can be used to overcome analytical bottlenecks in experiments with limited number of replicates and low sequencing coverage. The method is implemented in CORNAS (Coverage-dependent RNA-Seq), and is available at https://github.com/joel-lzb/CORNAS .

    Matched MeSH terms: Bayes Theorem
  15. Rovie-Ryan JJ, Khan FAA, Abdullah MT
    BMC Ecol Evol, 2021 02 15;21(1):26.
    PMID: 33588750 DOI: 10.1186/s12862-021-01757-1
    BACKGROUND: We analyzed a combined segment (2032-bp) of the sex-determining region and the testis-specific protein of the Y-chromosome (Y-DNA) gene to clarify the gene flow and phylogenetic relationships of the long-tailed macaques (Macaca fascicularis) in Southeast Asia. Phylogenetic relationships were constructed using the maximum likelihood, Bayesian inference, and the median-joining network from a total of 164 adult male M. fascicularis from 62 localities in Malaysia, including sequences from the other regions from previous studies.

    RESULTS: Based on Y-DNA, we confirm the presence of two lineages of M. fascicularis: the Indochinese and Sundaic lineages. The Indochinese lineage is represented by M. fascicularis located northwards of the Surat Thani-Krabi depression region and is introgressed by the Macaca mulatta Y-DNA. The Sundaic lineage is free from such hybridization event, thus defined as the original carrier of the M. fascicularis Y-DNA. We further revealed that the Sundaic lineage differentiated into two forms: the insular and the continental forms. The insular form, which represents the ancestral form of M. fascicularis, consists of two haplotypes: a single homogenous haplotype occupying the island of Borneo, Philippines, and southern Sumatra; and the Javan haplotype. The more diverse continental form consists of 17 haplotypes in which a dominant haplotype was shared by individuals from southern Thai Peninsular (south of Surat Thani-Krabi depression), Peninsular Malaysia, and Sumatra. Uniquely, Sumatra contains both the continental and insular Y-DNA which can be explained by a secondary contact hypothesis.

    CONCLUSIONS: Overall, the findings in this study are important: (1) to help authority particularly in Malaysia on the population management activities including translocation and culling of conflict M. fascicularis, (2) to identify the unknown origin of captive M. fascicularis used in biomedical research, and; (3) the separation between the continental and insular forms warrants for the treatment as separate management units.

    Matched MeSH terms: Bayes Theorem
  16. Nada Raja T, Hu TH, Zainudin R, Lee KS, Perkins SL, Singh B
    BMC Evol. Biol., 2018 04 10;18(1):49.
    PMID: 29636003 DOI: 10.1186/s12862-018-1170-9
    BACKGROUND: Non-human primates have long been identified to harbour different species of Plasmodium. Long-tailed macaques (Macaca fascicularis), in particular, are reservoirs for P. knowlesi, P. inui, P. cynomolgi, P. coatneyi and P. fieldi. A previous study conducted in Sarawak, Malaysian Borneo, however revealed that long-tailed macaques could potentially harbour novel species of Plasmodium based on sequences of small subunit ribosomal RNA and circumsporozoite genes. To further validate this finding, the mitochondrial genome and the apicoplast caseinolytic protease M genes of Plasmodium spp. were sequenced from 43 long-tailed macaque blood samples.

    RESULTS: Apart from several named species of malaria parasites, long-tailed macaques were found to be potentially infected with novel species of Plasmodium, namely one we refer to as "P. inui-like." This group of parasites bifurcated into two monophyletic clades indicating the presence of two distinct sub-populations. Further analyses, which relied on the assumption of strict co-phylogeny between hosts and parasites, estimated a population expansion event of between 150,000 to 250,000 years before present of one of these sub-populations that preceded that of the expansion of P. knowlesi. Furthermore, both sub-populations were found to have diverged from a common ancestor of P. inui approximately 1.5 million years ago. In addition, the phylogenetic analyses also demonstrated that long-tailed macaques are new hosts for P. simiovale.

    CONCLUSIONS: Malaria infections of long-tailed macaques of Sarawak, Malaysian Borneo are complex and include a novel species of Plasmodium that is phylogenetically distinct from P. inui. These macaques are new natural hosts of P. simiovale, a species previously described only in toque monkeys (Macaca sinica) in Sri Lanka. The results suggest that ecological factors could affect the evolution of malaria parasites.

    Matched MeSH terms: Bayes Theorem
  17. Aketarawong N, Isasawin S, Thanaphum S
    BMC Genet, 2014;15:70.
    PMID: 24929425 DOI: 10.1186/1471-2156-15-70
    Bactrocera dorsalis s.s. (Hendel) and B. papayae Drew & Hancock, are invasive pests belonging to the B. dorsalis complex. Their species status, based on morphology, is sometimes arguable. Consequently, the existence of cryptic species and/or population isolation may decrease the effectiveness of the sterile insect technique (SIT) due to an unknown degree of sexual isolation between released sterile flies and wild counterparts. To evaluate the genetic relationship and current demography in wild populations for guiding the application of area-wide integrated pest management using SIT, seven microsatellite-derived markers from B. dorsalis s.s. and another five from B. papayae were used for surveying intra- and inter-specific variation, population structure, and recent migration among sympatric and allopatric populations of the two morphological forms across Southern Thailand and West Malaysia.
    Matched MeSH terms: Bayes Theorem
  18. Kwong QB, Teh CK, Ong AL, Chew FT, Mayes S, Kulaveerasingam H, et al.
    BMC Genet, 2017 Dec 11;18(1):107.
    PMID: 29228905 DOI: 10.1186/s12863-017-0576-5
    BACKGROUND: Genomic selection (GS) uses genome-wide markers as an attempt to accelerate genetic gain in breeding programs of both animals and plants. This approach is particularly useful for perennial crops such as oil palm, which have long breeding cycles, and for which the optimal method for GS is still under debate. In this study, we evaluated the effect of different marker systems and modeling methods for implementing GS in an introgressed dura family derived from a Deli dura x Nigerian dura (Deli x Nigerian) with 112 individuals. This family is an important breeding source for developing new mother palms for superior oil yield and bunch characters. The traits of interest selected for this study were fruit-to-bunch (F/B), shell-to-fruit (S/F), kernel-to-fruit (K/F), mesocarp-to-fruit (M/F), oil per palm (O/P) and oil-to-dry mesocarp (O/DM). The marker systems evaluated were simple sequence repeats (SSRs) and single nucleotide polymorphisms (SNPs). RR-BLUP, Bayesian A, B, Cπ, LASSO, Ridge Regression and two machine learning methods (SVM and Random Forest) were used to evaluate GS accuracy of the traits.

    RESULTS: The kinship coefficient between individuals in this family ranged from 0.35 to 0.62. S/F and O/DM had the highest genomic heritability, whereas F/B and O/P had the lowest. The accuracies using 135 SSRs were low, with accuracies of the traits around 0.20. The average accuracy of machine learning methods was 0.24, as compared to 0.20 achieved by other methods. The trait with the highest mean accuracy was F/B (0.28), while the lowest were both M/F and O/P (0.18). By using whole genomic SNPs, the accuracies for all traits, especially for O/DM (0.43), S/F (0.39) and M/F (0.30) were improved. The average accuracy of machine learning methods was 0.32, compared to 0.31 achieved by other methods.

    CONCLUSION: Due to high genomic resolution, the use of whole-genome SNPs improved the efficiency of GS dramatically for oil palm and is recommended for dura breeding programs. Machine learning slightly outperformed other methods, but required parameters optimization for GS implementation.

    Matched MeSH terms: Bayes Theorem
  19. Yavari Nejad F, Varathan KD
    BMC Med Inform Decis Mak, 2021 04 30;21(1):141.
    PMID: 33931058 DOI: 10.1186/s12911-021-01493-y
    BACKGROUND: Dengue fever is a widespread viral disease and one of the world's major pandemic vector-borne infections, causing serious hazard to humanity. The World Health Organisation (WHO) reported that the incidence of dengue fever has increased dramatically across the world in recent decades. WHO currently estimates an annual incidence of 50-100 million dengue infections worldwide. To date, no tested vaccine or treatment is available to stop or prevent dengue fever. Thus, the importance of predicting dengue outbreaks is significant. The current issue that should be addressed in dengue outbreak prediction is accuracy. A limited number of studies have conducted an in-depth analysis of climate factors in dengue outbreak prediction.

    METHODS: The most important climatic factors that contribute to dengue outbreaks were identified in the current work. Correlation analyses were performed in order to determine these factors and these factors were used as input parameters for machine learning models. Top five machine learning classification models (Bayes network (BN) models, support vector machine (SVM), RBF tree, decision table and naive Bayes) were chosen based on past research. The models were then tested and evaluated on the basis of 4-year data (January 2010 to December 2013) collected in Malaysia.

    RESULTS: This research has two major contributions. A new risk factor, called the TempeRain factor (TRF), was identified and used as an input parameter for the model of dengue outbreak prediction. Moreover, TRF was applied to demonstrate its strong impact on dengue outbreaks. Experimental results showed that the Bayes Network model with the new meteorological risk factor identified in this study increased accuracy to 92.35% for predicting dengue outbreaks.

    CONCLUSIONS: This research explored the factors used in dengue outbreak prediction systems. The major contribution of this study is identifying new significant factors that contribute to dengue outbreak prediction. From the evaluation result, we obtained a significant improvement in the accuracy of a machine learning model for dengue outbreak prediction.

    Matched MeSH terms: Bayes Theorem
  20. Mohd Radzi SF, Hassan MS, Mohd Radzi MAH
    BMC Med Inform Decis Mak, 2022 Nov 24;22(1):306.
    PMID: 36434656 DOI: 10.1186/s12911-022-02050-x
    BACKGROUND: In healthcare area, big data, if integrated with machine learning, enables health practitioners to predict the result of a disorder or disease more accurately. In Autistic Spectrum Disorder (ASD), it is important to screen the patients to enable them to undergo proper treatments as early as possible. However, difficulties may arise in predicting ASD occurrences accurately, mainly caused by human errors. Data mining, if embedded into health screening practice, can help to overcome the difficulties. This study attempts to evaluate the performance of six best classifiers, taken from existing works, at analysing ASD screening training dataset.

    RESULT: We tested Naive Bayes, Logistic Regression, KNN, J48, Random Forest, SVM, and Deep Neural Network algorithms to ASD screening dataset and compared the classifiers' based on significant parameters; sensitivity, specificity, accuracy, receiver operating characteristic, area under the curve, and runtime, in predicting ASD occurrences. We also found that most of previous studies focused on classifying health-related dataset while ignoring the missing values which may contribute to significant impacts to the classification result which in turn may impact the life of the patients. Thus, we addressed the missing values by implementing imputation method where they are replaced with the mean of the available records found in the dataset.

    CONCLUSION: We found that J48 produced promising results as compared to other classifiers when tested in both circumstances, with and without missing values. Our findings also suggested that SVM does not necessarily perform well for small and simple datasets. The outcome is hoped to assist health practitioners in making accurate diagnosis of ASD occurrences in patients.

    Matched MeSH terms: Bayes Theorem
Filters
Contact Us

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

External Links