MyMedR

Displaying publications 1 - 20 of 104 in total

Abstract:

Sort:

Fulltext 3-Dimensional facial expression recognition in human using multi-points warping

Agbolade O, Nazri A, Yaakob R, Ghani AA, Cheah YK

BMC Bioinformatics, 2019 Dec 02;20(1):619.
PMID: 31791234 DOI: 10.1186/s12859-019-3153-2

BACKGROUND: Expression in H-sapiens plays a remarkable role when it comes to social communication. The identification of this expression by human beings is relatively easy and accurate. However, achieving the same result in 3D by machine remains a challenge in computer vision. This is due to the current challenges facing facial data acquisition in 3D; such as lack of homology and complex mathematical analysis for facial point digitization. This study proposes facial expression recognition in human with the application of Multi-points Warping for 3D facial landmark by building a template mesh as a reference object. This template mesh is thereby applied to each of the target mesh on Stirling/ESRC and Bosphorus datasets. The semi-landmarks are allowed to slide along tangents to the curves and surfaces until the bending energy between a template and a target form is minimal and localization error is assessed using Procrustes ANOVA. By using Principal Component Analysis (PCA) for feature selection, classification is done using Linear Discriminant Analysis (LDA).
RESULT: The localization error is validated on the two datasets with superior performance over the state-of-the-art methods and variation in the expression is visualized using Principal Components (PCs). The deformations show various expression regions in the faces. The results indicate that Sad expression has the lowest recognition accuracy on both datasets. The classifier achieved a recognition accuracy of 99.58 and 99.32% on Stirling/ESRC and Bosphorus, respectively.
CONCLUSION: The results demonstrate that the method is robust and in agreement with the state-of-the-art results.

Matched MeSH terms: Discriminant Analysis
Fulltext A Comparative Characterization of Physicochemical and Antioxidants Properties of Processed Heterotrigona itama Honey from Different Origins and Classification by Chemometrics Analysis

Shamsudin S, Selamat J, Sanny M, A R SB, Jambari NN, Khatib A

Molecules, 2019 Oct 29;24(21).
PMID: 31671885 DOI: 10.3390/molecules24213898

Stingless bee honey produced by Heterotrigona itama from different botanical origins was characterised and discriminated. Three types of stingless bee honey collected from acacia, gelam, and starfruit nectars were analyzed and compared with Apis mellifera honey. The results showed that stingless bee honey samples from the three different botanical origins were significantly different in terms of their moisture content, pH, free acidity, total soluble solids, colour characteristics, sugar content, amino acid content and antioxidant properties. Stingless bee honey was significantly different from Apis mellifera honey in terms of physicochemical and antioxidant properties. The amino acid content was further used in the chemometrics analysis to evaluate the role of amino acid in discriminating honey according to botanical origin. Partial least squares-discriminant analysis (PLS-DA) revealed that the stingless bee honey was completely distinguishable from Apis mellifera honey. Notably, a clear distinction between the stingless bee honey types was also observed. The specific amino acids involved in the distinction of honey were cysteine for acacia and gelam, phenylalanine and 3-hydroxyproline for starfruit, and proline for Apis mellifera honey. The results showed that all honey samples were successfully classified based on amino acid content.

Matched MeSH terms: Discriminant Analysis
A discrimination method for the detection of pneumonia using chest radiograph

Noor NM, Rijal OM, Yunus A, Abu-Bakar SA

Comput Med Imaging Graph, 2010 Mar;34(2):160-6.
PMID: 19758785 DOI: 10.1016/j.compmedimag.2009.08.005

This paper presents a statistical method for the detection of lobar pneumonia when using digitized chest X-ray films. Each region of interest was represented by a vector of wavelet texture measures which is then multiplied by the orthogonal matrix Q(2). The first two elements of the transformed vectors were shown to have a bivariate normal distribution. Misclassification probabilities were estimated using probability ellipsoids and discriminant functions. The result of this study recommends the detection of pneumonia by constructing probability ellipsoids or discriminant function using maximum energy and maximum column sum energy texture measures where misclassification probabilities were less than 0.15.

Matched MeSH terms: Discriminant Analysis
Fulltext A hybrid sensing approach for pure and adulterated honey classification

Subari N, Mohamad Saleh J, Md Shakaff AY, Zakaria A

Sensors (Basel), 2012;12(10):14022-40.
PMID: 23202033 DOI: 10.3390/s121014022

This paper presents a comparison between data from single modality and fusion methods to classify Tualang honey as pure or adulterated using Linear Discriminant Analysis (LDA) and Principal Component Analysis (PCA) statistical classification approaches. Ten different brands of certified pure Tualang honey were obtained throughout peninsular Malaysia and Sumatera, Indonesia. Various concentrations of two types of sugar solution (beet and cane sugar) were used in this investigation to create honey samples of 20%, 40%, 60% and 80% adulteration concentrations. Honey data extracted from an electronic nose (e-nose) and Fourier Transform Infrared Spectroscopy (FTIR) were gathered, analyzed and compared based on fusion methods. Visual observation of classification plots revealed that the PCA approach able to distinct pure and adulterated honey samples better than the LDA technique. Overall, the validated classification results based on FTIR data (88.0%) gave higher classification accuracy than e-nose data (76.5%) using the LDA technique. Honey classification based on normalized low-level and intermediate-level FTIR and e-nose fusion data scored classification accuracies of 92.2% and 88.7%, respectively using the Stepwise LDA method. The results suggested that pure and adulterated honey samples were better classified using FTIR and e-nose fusion data than single modality data.

Matched MeSH terms: Discriminant Analysis
A new hybrid intelligent system for accurate detection of Parkinson's disease

Hariharan M, Polat K, Sindhu R

Comput Methods Programs Biomed, 2014 Mar;113(3):904-13.
PMID: 24485390 DOI: 10.1016/j.cmpb.2014.01.004

Elderly people are commonly affected by Parkinson's disease (PD) which is one of the most common neurodegenerative disorders due to the loss of dopamine-producing brain cells. People with PD's (PWP) may have difficulty in walking, talking or completing other simple tasks. Variety of medications is available to treat PD. Recently, researchers have found that voice signals recorded from the PWP is becoming a useful tool to differentiate them from healthy controls. Several dysphonia features, feature reduction/selection techniques and classification algorithms were proposed by researchers in the literature to detect PD. In this paper, hybrid intelligent system is proposed which includes feature pre-processing using Model-based clustering (Gaussian mixture model), feature reduction/selection using principal component analysis (PCA), linear discriminant analysis (LDA), sequential forward selection (SFS) and sequential backward selection (SBS), and classification using three supervised classifiers such as least-square support vector machine (LS-SVM), probabilistic neural network (PNN) and general regression neural network (GRNN). PD dataset was used from University of California-Irvine (UCI) machine learning database. The strength of the proposed method has been evaluated through several performance measures. The experimental results show that the combination of feature pre-processing, feature reduction/selection methods and classification gives a maximum classification accuracy of 100% for the Parkinson's dataset.

Matched MeSH terms: Discriminant Analysis
Fulltext A novel investigation of the effect of iterations in sliding semi-landmarks for 3D human facial images

Nazri A, Agbolade O, Yaakob R, Ghani AA, Cheah YK

BMC Bioinformatics, 2020 May 24;21(1):208.
PMID: 32448182 DOI: 10.1186/s12859-020-3497-7

BACKGROUND: Landmark-based approaches of two- or three-dimensional coordinates are the most widely used in geometric morphometrics (GM). As human face hosts the organs that act as the central interface for identification, more landmarks are needed to characterize biological shape variation. Because the use of few anatomical landmarks may not be sufficient for variability of some biological patterns and form, sliding semi-landmarks are required to quantify complex shape.
RESULTS: This study investigates the effect of iterations in sliding semi-landmarks and their results on the predictive ability in GM analyses of soft-tissue in 3D human face. Principal Component Analysis (PCA) is used for feature selection and the gender are predicted using Linear Discriminant Analysis (LDA) to test the effect of each relaxation state. The results show that the classification accuracy is affected by the number of iterations but not in progressive pattern. Also, there is stability at 12 relaxation state with highest accuracy of 96.43% and an unchanging decline after the 12 relaxation state.
CONCLUSIONS: The results indicate that there is a particular number of iteration or cycle where the sliding becomes optimally relaxed. This means the higher the number of iterations is not necessarily the higher the accuracy.

Matched MeSH terms: Discriminant Analysis
A novel method of determining breast cancer risk using parenchymal textural analysis of mammography images on an Asian cohort

Tan M, Mariapun S, Yip CH, Ng KH, Teo SH

Phys Med Biol, 2019 01 31;64(3):035016.
PMID: 30577031 DOI: 10.1088/1361-6560/aafabd

Historically, breast cancer risk prediction models are based on mammographic density measures, which are dichotomous in nature and generally categorize each voxel or area of the breast parenchyma as 'dense' or 'not dense'. Using these conventional methods, the structural patterns or textural components of the breast tissue elements are not considered or ignored entirely. This study presents a novel method to predict breast cancer risk that combines new texture and mammographic density based image features. We performed a comprehensive study of the correlation of 944 new and conventional texture and mammographic density features with breast cancer risk on a cohort of Asian women. We studied 250 breast cancer cases and 250 controls matched at full-field digital mammography (FFDM) status for age, BMI and ethnicity. Stepwise regression analysis identified relevant features to be included in a linear discriminant analysis (LDA) classifier model, trained and tested using a leave-one-out based cross-validation method. The area under the receiver operating characteristic (AUC) and adjusted odds ratios (ORs) were used as the two performance assessment indices in our study. For the LDA trained classifier, the adjusted OR was 6.15 (95% confidence interval: 3.55-10.64) and for Volpara volumetric breast density, 1.10 (0.67-1.81). The AUC for the LDA trained classifier was 0.68 (0.64-0.73), compared to 0.52 (0.47-0.57) for Volpara volumetric breast density (p

Matched MeSH terms: Discriminant Analysis
Analysis of dog meat adulteration in beef meatballs using non-targeted UHPLC-Orbitrap HRMS metabolomics and chemometrics for halal authentication study

Windarsih A, Bakar NKA, Rohman A, Erwanto Y

Anal Sci, 2024 Mar;40(3):385-397.
PMID: 38095741 DOI: 10.1007/s44211-023-00470-x

Due to the different price and high quality, halal meat such as beef can be adulterated with non-halal meat with low price to get an economical price. The objective of this research was to develop an analytical method for halal authentication testing of beef meatballs (BM) from dog meat (DM) using a non-targeted metabolomics approach employing liquid chromatography-high-resolution mass spectrometry (LC-HRMS) and chemometrics. The differentiation of authentic BM from that adulterated with DM was successfully performed using partial least square-discriminant analysis (PLS-DA) with high accuracy (R2X = 0.980, and R2Y = 0.980) and good predictivity (Q2 = 0.517). In addition, partial least square (PLS) and orthogonal PLS (OPLS) were successfully used to predict the DM added (% w/w) in BM with high accuracy (R2 > 0.990). A number of metabolites, potential for biomarker candidates, were identified to differentiate BM and that adulterated with DM. It showed that the combination of a non-targeted LC-HRMS Orbitrap metabolomics and chemometrics could detect up to 0.1% w/w of DM adulteration. The developed method was successfully applied for analysis of commercial meatball samples (n = 28). Moreover, pathway analysis revealed that beta-alanine, histidine, and ether lipid metabolism were significantly affected by dog meat adulteration. In summary, this developed method has great potential to be developed and used as an alternative method for analysis of non-halal meats in halal meat products.

Matched MeSH terms: Discriminant Analysis
Analysis of geometric moments as features for firearm identification

Md Ghani NA, Liong CY, Jemain AA

Forensic Sci Int, 2010 May 20;198(1-3):143-9.
PMID: 20211535 DOI: 10.1016/j.forsciint.2010.02.011

The task of identifying firearms from forensic ballistics specimens is exacting in crime investigation since the last two decades. Every firearm, regardless of its size, make and model, has its own unique 'fingerprint'. These fingerprints transfer when a firearm is fired to the fired bullet and cartridge case. The components that are involved in producing these unique characteristics are the firing chamber, breech face, firing pin, ejector, extractor and the rifling of the barrel. These unique characteristics are the critical features in identifying firearms. It allows investigators to decide on which particular firearm that has fired the bullet. Traditionally the comparison of ballistic evidence has been a tedious and time-consuming process requiring highly skilled examiners. Therefore, the main objective of this study is the extraction and identification of suitable features from firing pin impression of cartridge case images for firearm recognition. Some previous studies have shown that firing pin impression of cartridge case is one of the most important characteristics used for identifying an individual firearm. In this study, data are gathered using 747 cartridge case images captured from five different pistols of type 9mm Parabellum Vektor SP1, made in South Africa. All the images of the cartridge cases are then segmented into three regions, forming three different set of images, i.e. firing pin impression image, centre of firing pin impression image and ring of firing pin impression image. Then geometric moments up to the sixth order were generated from each part of the images to form a set of numerical features. These 48 features were found to be significantly different using the MANOVA test. This high dimension of features is then reduced into only 11 significant features using correlation analysis. Classification results using cross-validation under discriminant analysis show that 96.7% of the images were classified correctly. These results demonstrate the value of geometric moments technique for producing a set of numerical features, based on which the identification of firearms are made.

Matched MeSH terms: Discriminant Analysis
Fulltext Anthropometric analysis of mandible: an important step for sex determination

Alias A, Ibrahim A, Abu Bakar SN, Swarhib Shafie M, Das S, Abdullah N, et al.

Clin Ter, 2018 11 6;169(5):e217-e223.
PMID: 30393808 DOI: 10.7417/CT.2018.2082

INTRODUCTION: The first step in the forensic identification is sex determination followed by age and stature estimation, as both are sex-dependent. The mandible is the largest, strongest and most durable bone in the face. Mandible is important for sex confirmation in absence of a complete pelvis and skull.
AIM: The aim of the present study was to determine sex of human mandible from morphology, morphometric measurements as well as discriminant function analysis from the CT scan.
MATERIALS AND METHODS: The present retrospective study comprised 79 subjects (48 males, 31 females), with age group between 18 and 74 years, and were obtained from the post mortem computed tomography data in the Hospital Kuala Lumpur. The parameters were divided into three morphologic and nine morphometric parameters, which were measured by using Osirix MD Software 3D Volume Rendering.
RESULTS: The Chi-square test showed that men were significantly association with square-shaped chin (92%), prominent muscle marking (85%) and everted gonial glare, whereas women had pointed chin (84%), less prominent muscle marking (90%) and inverted gonial glare (80%). All parameter measurements showed significantly greater values in males than in females by independent t-test (p< 0.01). By discriminant analysis, the classification accuracy was 78.5%, the sensitivity was 79.2% and the specificity was 77.4%. The discriminant function equation was formulated based on bigonial breath and condylar height, which were the best predictors.
CONCLUSION: In conclusion, the mandible could be distinguished according to the sex. The results of the study can be used for identification of damaged and/or unknown mandible in the Malaysian population.

Matched MeSH terms: Discriminant Analysis
Application of FTIR-ATR spectroscopy coupled with multivariate analysis for rapid estimation of butter adulteration

Fadzlillah NA, Rohman A, Ismail A, Mustafa S, Khatib A

J Oleo Sci, 2013;62(8):555-62.
PMID: 23985484

In dairy product sector, butter is one of the potential sources of fat soluble vitamins, namely vitamin A, D, E, K; consequently, butter is taken into account as high valuable price from other dairy products. This fact has attracted unscrupulous market players to blind butter with other animal fats to gain economic profit. Animal fats like mutton fat (MF) are potential to be mixed with butter due to the similarity in terms of fatty acid composition. This study focused on the application of FTIR-ATR spectroscopy in conjunction with chemometrics for classification and quantification of MF as adulterant in butter. The FTIR spectral region of 3910-710 cm⁻¹ was used for classification between butter and butter blended with MF at various concentrations with the aid of discriminant analysis (DA). DA is able to classify butter and adulterated butter without any mistakenly grouped. For quantitative analysis, partial least square (PLS) regression was used to develop a calibration model at the frequency regions of 3910-710 cm⁻¹. The equation obtained for the relationship between actual value of MF and FTIR predicted values of MF in PLS calibration model was y = 0.998x + 1.033, with the values of coefficient of determination (R²) and root mean square error of calibration are 0.998 and 0.046% (v/v), respectively. The PLS calibration model was subsequently used for the prediction of independent samples containing butter in the binary mixtures with MF. Using 9 principal components, root mean square error of prediction (RMSEP) is 1.68% (v/v). The results showed that FTIR spectroscopy can be used for the classification and quantification of MF in butter formulation for verification purposes.

Matched MeSH terms: Discriminant Analysis
Fulltext Application of partial least squares discriminant analysis for discrimination of palm oils

Mas Ezatul Nadia Mohd Ruah, Nor Fazila Rasaruddin, Fong, Sim Siong, Mohd Zuli Jaafar

Scientific Research Journal, 2014;11(1):0-0.
MyJurnal

This paper outlines the application of chemometrics and pattern recognition tools to classify palm oil using Fourier Transform Mid Infrared spectroscopy (FT-MIR). FT-MIR spectroscopy is used as an effective analytical tool in order to categorise the oil into the category of unused palm oil and used palm oil for frying. The samples used in this study consist of 28 types of pure palm oil, and 28 types of frying palm oils. FT-MIR spectral was obtained in absorbance mode at the spectral range from 650 cm -1 to 4000 cm -1 using FT-MIR-ATR sample handling. The aim of this work is to develop fast method in discriminating the palm oils by implementing Partial Least Square Discriminant Analysis (PLS-DA), Learning Vector Quantisation (LVQ) and Support Vector Machine (SVM). Raw FT-MIR spectra were subjected to Savitzky-Golay smoothing and standardized before developing the classification models. The classification model was validated through finding the value of percentage correctly classified by test set for every model in order to show which classifier provided the best classification. In order to improve the performance of the classification model, variable selection method known as t-statistic method was applied. The significant variable in developing classification model was selected through this method. The result revealed that PLSDA classifier of the standardized data with application of t-statistic showed the best performance with highest percentage correctly classified among the classifiers.

Matched MeSH terms: Discriminant Analysis
Applied chemometric approach in identification sources of air quality pattern in Selangor, Malaysia

Ang KH

Sains Malaysiana, 2018;47:471-479.

In recent years, Malaysia has experienced quite a few number of chronic air pollution problems and it has become a
major contributor to the deterioration of human health and ecosystems. This study aimed to assess the air quality data
and identify the pattern of air pollution sources using chemometric analysis through hierarchical cluster analysis (HCA),
discriminant analysis (DA), principal component analysis (PCA) and multiple linear regression analysis (MLR). The air
quality data from January 2016 until December 2016 was obtained from the Department of Environment Malaysia. Air
quality data from eight sampling stations in Selangor include the selected variables of nitrogen dioxide (NO2
), ozone (O3
),
sulfur dioxide (SO2
), carbon monoxide (CO) and particulate matter (PM10). The HCA resulted in three clusters, namely low
pollution source (LPS), moderate pollution source (MPS) and slightly high pollution source (SHPS). Meanwhile, DA resulted
in two and four variables for the forward stepwise mode and the backward stepwise mode, respectively. Through PCA,
it was identified that the main pollutants of LPS, MPS and SHPS came from industrial and vehicle emissions, agricultural
systems, residential factors and natural emission sources. Among the three models yielded from the MLR analysis, it was
found that SHPS is the most suitable model to be used for the prediction of Air Pollution Index. This study concluded that
a clearer review and practical design of air quality monitoring network would be beneficial for better management of
air pollution. The study also suggested that chemometric techniques have the ability to show significant information on
spatial variability for large and complex air quality data.

Matched MeSH terms: Discriminant Analysis
Assessment of arsenic and heavy metal contents in cockles (Anadara granosa) using multivariate statistical techniques

Abbas Alkarkhi FM, Ismail N, Easa AM

J Hazard Mater, 2008 Feb 11;150(3):783-9.
PMID: 17590506

Cockles (Anadara granosa) sample obtained from two rivers in the Penang State of Malaysia were analyzed for the content of arsenic (As) and heavy metals (Cr, Cd, Zn, Cu, Pb, and Hg) using a graphite flame atomic absorption spectrometer (GF-AAS) for Cr, Cd, Zn, Cu, Pb, As and cold vapor atomic absorption spectrometer (CV-AAS) for Hg. The two locations of interest with 20 sampling points of each location were Kuala Juru (Juru River) and Bukit Tambun (Jejawi River). Multivariate statistical techniques such as multivariate analysis of variance (MANOVA) and discriminant analysis (DA) were applied for analyzing the data. MANOVA showed a strong significant difference between the two rivers in term of As and heavy metals contents in cockles. DA gave the best result to identify the relative contribution for all parameters in discriminating (distinguishing) the two rivers. It provided an important data reduction as it used only two parameters (Zn and Cd) affording more than 72% correct assignations. Results indicated that the two rivers were different in terms of As and heavy metal contents in cockle, and the major difference was due to the contribution of Zn and Cd. A positive correlation was found between discriminate functions (DF) and Zn, Cd and Cr, whereas negative correlation was exhibited with other heavy metals. Therefore, DA allowed a reduction in the dimensionality of the data set, delineating a few indicator parameters responsible for large variations in heavy metals and arsenic content. Taking into account of these results, it can be suggested that a continuous monitoring of As and heavy metals in cockles be performed in these two rivers.

Matched MeSH terms: Discriminant Analysis
Fulltext Assessment of physical properties of ripe banana flour prepared from two varieties: Cavendish and Dream banana

Abbas, F.M.A., Saifullah, R., Azhar, M.E.

International Food Research Journal, 2009;16(2):183-189.
MyJurnal

Physical properties of ripe banana flour were studied in Cavendish and Dream banana, in order to distinguish the two varieties. Flour was analyzed for pH, total soluble solids (TSS), water holding capacity
(WHC) and oil holding capacity (OHC) at 40, 60 and 80 °C, color values L*, a* and b*, back extrusion force
and viscosity. Physical properties data were analyzed by cluster analysis (CA) and discriminant analysis (DA). CA showed that the two types of flour were different in terms of selected physical properties. DA indicated that WHC at 60 °C was the main contributor in discriminating the two types of flour.

Matched MeSH terms: Discriminant Analysis
Authentication analysis of red fruit (Pandanus Conoideus Lam) oil using FTIR spectroscopy in combination with chemometrics

Rohman A, Man YB, Riyanto S

Phytochem Anal, 2011 Sep-Oct;22(5):462-7.
PMID: 22033916 DOI: 10.1002/pca.1304

Red fruit (Pandanus conoideus Lam) is endemic plant of Papua, Indonesia and Papua New Guinea. The price of its oil (red fruit oil, RFO) is 10-15 times higher than that of common vegetable oils; consequently, RFO is subjected to adulteration with lower price oils. Among common vegetable oils, canola oil (CaO) and rice bran oil (RBO) have similar fatty acid profiles to RFO as indicated by the score plot of principal component analysis; therefore, CaO and RBO are potential adulterants in RFO.

Matched MeSH terms: Discriminant Analysis
Automated characterization of fatty liver disease and cirrhosis using curvelet transform and entropy features extracted from ultrasound images

Acharya UR, Raghavendra U, Fujita H, Hagiwara Y, Koh JE, Jen Hong T, et al.

Comput Biol Med, 2016 12 01;79:250-258.
PMID: 27825038 DOI: 10.1016/j.compbiomed.2016.10.022

Fatty liver disease (FLD) is reversible disease and can be treated, if it is identified at an early stage. However, if diagnosed at the later stage, it can progress to an advanced liver disease such as cirrhosis which may ultimately lead to death. Therefore, it is essential to detect it at an early stage before the disease progresses to an irreversible stage. Several non-invasive computer-aided techniques are proposed to assist in the early detection of FLD and cirrhosis using ultrasound images. In this work, we are proposing an algorithm to discriminate automatically the normal, FLD and cirrhosis ultrasound images using curvelet transform (CT) method. Higher order spectra (HOS) bispectrum, HOS phase, fuzzy, Kapoor, max, Renyi, Shannon, Vajda and Yager entropies are extracted from CT coefficients. These extracted features are subjected to locality sensitive discriminant analysis (LSDA) feature reduction method. Then these LSDA coefficients ranked based on F-value are fed to different classifiers to choose the best performing classifier using minimum number of features. Our proposed technique can characterize normal, FLD and cirrhosis using probabilistic neural network (PNN) classifier with an accuracy of 97.33%, specificity of 100.00% and sensitivity of 96.00% using only six features. In addition, these chosen features are used to develop a liver disease index (LDI) to differentiate the normal, FLD and cirrhosis classes using a single number. This can significantly help the radiologists to discriminate FLD and cirrhosis in their routine liver screening.

Matched MeSH terms: Discriminant Analysis
Fulltext Automated classification of tropical shrub species: a hybrid of leaf shape and machine learning approach

Murat M, Chang SW, Abu A, Yap HJ, Yong KT

PeerJ, 2017;5:e3792.
PMID: 28924506 DOI: 10.7717/peerj.3792

Plants play a crucial role in foodstuff, medicine, industry, and environmental protection. The skill of recognising plants is very important in some applications, including conservation of endangered species and rehabilitation of lands after mining activities. However, it is a difficult task to identify plant species because it requires specialized knowledge. Developing an automated classification system for plant species is necessary and valuable since it can help specialists as well as the public in identifying plant species easily. Shape descriptors were applied on the myDAUN dataset that contains 45 tropical shrub species collected from the University of Malaya (UM), Malaysia. Based on literature review, this is the first study in the development of tropical shrub species image dataset and classification using a hybrid of leaf shape and machine learning approach. Four types of shape descriptors were used in this study namely morphological shape descriptors (MSD), Histogram of Oriented Gradients (HOG), Hu invariant moments (Hu) and Zernike moments (ZM). Single descriptor, as well as the combination of hybrid descriptors were tested and compared. The tropical shrub species are classified using six different classifiers, which are artificial neural network (ANN), random forest (RF), support vector machine (SVM), k-nearest neighbour (k-NN), linear discriminant analysis (LDA) and directed acyclic graph multiclass least squares twin support vector machine (DAG MLSTSVM). In addition, three types of feature selection methods were tested in the myDAUN dataset, Relief, Correlation-based feature selection (CFS) and Pearson's coefficient correlation (PCC). The well-known Flavia dataset and Swedish Leaf dataset were used as the validation dataset on the proposed methods. The results showed that the hybrid of all descriptors of ANN outperformed the other classifiers with an average classification accuracy of 98.23% for the myDAUN dataset, 95.25% for the Flavia dataset and 99.89% for the Swedish Leaf dataset. In addition, the Relief feature selection method achieved the highest classification accuracy of 98.13% after 80 (or 60%) of the original features were reduced, from 133 to 53 descriptors in the myDAUN dataset with the reduction in computational time. Subsequently, the hybridisation of four descriptors gave the best results compared to others. It is proven that the combination MSD and HOG were good enough for tropical shrubs species classification. Hu and ZM descriptors also improved the accuracy in tropical shrubs species classification in terms of invariant to translation, rotation and scale. ANN outperformed the others for tropical shrub species classification in this study. Feature selection methods can be used in the classification of tropical shrub species, as the comparable results could be obtained with the reduced descriptors and reduced in computational time and cost.

Matched MeSH terms: Discriminant Analysis
Automated diabetic macular edema (DME) grading system using DWT, DCT Features and maculopathy index

Acharya UR, Mookiah MRK, Koh JEW, Tan JH, Bhandary SV, Rao AK, et al.

Comput Biol Med, 2017 05 01;84:59-68.
PMID: 28343061 DOI: 10.1016/j.compbiomed.2017.03.016

The cause of diabetic macular edema (DME) is due to prolonged and uncontrolled diabetes mellitus (DM) which affects the vision of diabetic subjects. DME is graded based on the exudate location from the macula. It is clinically diagnosed using fundus images which is tedious and time-consuming. Regular eye screening and subsequent treatment may prevent the vision loss. Hence, in this work, a hybrid system based on Radon transform (RT), discrete wavelet transform (DWT) and discrete cosine transform (DCT) are proposed for an automated detection of DME. The fundus images are subjected to RT to obtain sinograms and DWT is applied on these sinograms to extract wavelet coefficients (approximate, horizontal, vertical and diagonal). DCT is applied on approximate coefficients to obtain 2D-DCT coefficients. Further, these coefficients are converted into 1D vector by arranging the coefficients in zig-zag manner. This 1D signal is subjected to locality sensitive discriminant analysis (LSDA). Finally, various supervised classifiers are used to classify the three classes using significant features. Our proposed technique yielded a classification accuracy of 100% and 97.01% using two and seven significant features for private and public (MESSIDOR) databases respectively. Also, a maculopathy index is formulated with two significant parameters to discriminate the three groups distinctly using a single integer. Hence, our obtained results suggest that this system can be used as an eye screening tool for diabetic subjects for DME.

Matched MeSH terms: Discriminant Analysis
Fulltext Changes in the urinary metabolites in losartan-treated spontaneously hypertensive rats

Norasikin Ab Azis, Mohd Saleh Ahmad Kamal, Zurain Radjeni, Ahmed Mediani, Renu Agarwal

Journal of Clinical and Health Sciences, 2021;6(1):32-45.
MyJurnal

Introduction: This study examined the association of losartan induced changes in urinary
metabolomic profile with the changes in blood pressure (BP) and renin-angiotensinaldosterone system (RAAS) in spontaneously hypertensive rats (SHR). Methods: Male SHR
were administered with either 0.5 mL of distilled water (control group, n=6) or 10 mg.kg-1 of
losartan (group 2, n=6) daily by oral gavage for 4 weeks. Body weight, BP, food and water
intake were measured weekly. At week 4, urine was collected for urinary electrolyte analysis
and metabolite profiling, after which the animals were euthanised by decapitation and blood
was collected for analysis of components of RAAS and electrolyte concentrations. Urine
metabolite profile of SHR was determined using proton nuclear magnetic resonance (
1H-NMR)
spectrometry combined with multivariate data analysis. Results: At week 4, losartan-treated
SHR had significantly lower BP than non-treated SHR. There were no differences in water
and food intake, body weight, serum and urinary electrolyte concentrations or in their urinary
excretions between the two groups. No differences were evident in the components of RAAS
except that the angiotensinogen level was significantly higher in losartan-treated SHR
compared to non-treated SHR. Orthogonal partial least squares discriminant analysis (OPLSDA) showed clear separation of urinary metabolites between control and losartan-treated
SHR. Losartan-treated SHR group was separated from the control group by changes in the
intermediates involved in glycine, serine and threonine metabolism. Conclusion:
Antihypertensive effect of losartan in SHR seems to be associated with changes in urinary
metabolite profile, particularly involving the metabolism of glycine, serine and threonine.

Matched MeSH terms: Discriminant Analysis

Filters

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

External Links