MyMedR

Displaying publications 21 - 40 of 265 in total

Abstract:

Sort:

Fulltext A preliminary study on automated freshwater algae recognition and classification system

Mosleh MA, Manssor H, Malek S, Milow P, Salleh A

BMC Bioinformatics, 2012;13 Suppl 17:S25.
PMID: 23282059 DOI: 10.1186/1471-2105-13-S17-S25

Freshwater algae can be used as indicators to monitor freshwater ecosystem condition. Algae react quickly and predictably to a broad range of pollutants. Thus they provide early signals of worsening environment. This study was carried out to develop a computer-based image processing technique to automatically detect, recognize, and identify algae genera from the divisions Bacillariophyta, Chlorophyta and Cyanobacteria in Putrajaya Lake. Literature shows that most automated analyses and identification of algae images were limited to only one type of algae. Automated identification system for tropical freshwater algae is even non-existent and this study is partly to fill this gap.

Matched MeSH terms: Principal Component Analysis
A probability distribution of shape for the dental maxillary arch using digital images

Rijal OM, Abdullah NA, Isa ZM, Noor NM, Tawfiq OF

Annu Int Conf IEEE Eng Med Biol Soc, 2012;2012:5420-3.
PMID: 23367155 DOI: 10.1109/EMBC.2012.6347220

Selected landmarks from each of 47 maxillary dental casts were used to define a Cartesian-coordinate system from which the positions of selected teeth were determined on standardized digital images. The position of the i-th tooth was defined by a line of length (l(i)) joining the tooth to the origin, and the angle (θ(i)) of this line to the horizontal Cartesian axis. Four teeth, the central incisor, lateral incisor, canine and first molar were selected and their position were collectively used to represent the shape of the dental arch. A pilot study using clustering and principal component analysis strongly suggest the existence of 3 groups of arch shape. In this study, the homogeneity of the 3 groups was further investigated and confirmed by the Dunn and Davies-Bouldein validity indices. This is followed by an investigation of the probability distribution of these 3 groups. The main result of this study suggests 3 groups of multivariate (MV) normal distribution. The MV normal probability distribution of these groups may be used in further studies to investigate the issues of variation of arch shape, which is fundamental to the practice of prosthodontics and orthodontics.

Matched MeSH terms: Principal Component Analysis
A simple approach for rapid detection and quantification of adulterants in stingless bees (Heterotrigona itama) honey

Se KW, Ghoshal SK, Wahab RA, Ibrahim RKR, Lani MN

Food Res Int, 2018 03;105:453-460.
PMID: 29433236 DOI: 10.1016/j.foodres.2017.11.012

In this study, we propose an easy approach by combining the Fourier transform infrared and attenuated total reflectance (FTIR-ATR) spectroscopy together with chemometrics analysis for rapid detection and accurate quantification of five adulterants such as fructose, glucose, sucrose, corn syrup and cane sugar in stingless bees (Heterotrigona itama) honey harvested in Malaysia. Adulterants were classified using principal component analysis and soft independent modeling class analogy, where the first derivative of the spectra in the wavenumber range of 1180-750cm-1 was utilized. The protocol could satisfactorily discriminate the stingless bees honey samples that were adulterated with the concentrations of corn syrup above 8% (w/w) and cane sugar over 2% (w/w). Feasibility of integrating FTIR-ATR with chemometrics for precise quantification of the five adulterants was affirmed using partial least square regression (PLSR) analysis. The study found that optimal PLSR analysis achieved standard error of calibrations and standard error of predictions within an acceptable range of 0.686-1.087% and 0.581-1.489%, respectively, indicating good predictive capability. Hence, the method developed here for detecting and quantifying adulteration in H. itama honey samples is accurate and rapid, requiring only 7-8min to complete as compared to 3h for the standard method, AOAC method 998.12.

Matched MeSH terms: Principal Component Analysis
A simplified clustering method for novice narcotic chemists

Chan KW, Tan GH, Wong RC

Sci Justice, 2012 Sep;52(3):136-41.
PMID: 22841136 DOI: 10.1016/j.scijus.2012.04.006

Statistical classification remains the most useful statistical tool for forensic chemists to assess the relationships between samples. Many clustering techniques such as principal component analysis and hierarchical cluster analysis have been employed to analyze chemical data for pattern recognition. Due to the feeble foundation of this statistics knowledge among novice drug chemists, a tetrahedron method was designed to simulate how advanced chemometrics operates. In this paper, the development of the graphical tetrahedron and computational matrices derived from the possible tetrahedrons are discussed. The tetrahedron method was applied to four selected parameters obtained from nine illicit heroin samples. Pattern analysis and mathematical computation of the differences in areas for assessing the dissimilarity between the nine tetrahedrons were found to be user-convenient and straightforward for novice cluster analysts.

Matched MeSH terms: Principal Component Analysis
A study of community structure and beta diversity of epiphyllous liverwort assemblages in Sabah, Malaysian Borneo

Pócs T, Lee GE, Podani J, Pesiu E, Havasi J, Tang HY, et al.

PhytoKeys, 2020;153:63-83.
PMID: 32765181 DOI: 10.3897/phytokeys.153.53637

We evaluated the species richness and beta diversity of epiphyllous assemblages from three selected localities in Sabah, i.e. Mt. Silam in Sapagaya Forest Reserve, and Ulu Senagang and Mt. Alab in Crocker Range Park. A total of 98 species were found and a phytosociological survey was carried out based on the three study areas. A detailed statistical analysis including standard correlation and regression analyses, ordination of species and leaves using centered principal component analysis, and the SDR simplex method to evaluate the beta diversity, was conducted. Beta diversity is very high in the epiphyllous liverwort assemblages in Sabah, with species replacement as the major component of pattern formation and less pronounced richness difference. The community analysis of the epiphyllous communities in Sabah makes possible their detailed description and comparison with similar communities of other continents.

Matched MeSH terms: Principal Component Analysis
Fulltext AMMI and GGE biplot analysis for yield performance and stability assessment of selected Bambara groundnut (Vigna subterranea L. Verdc.) genotypes under the multi-environmental trails (METs)

Khan MMH, Rafii MY, Ramlee SI, Jusoh M, Al Mamun M

Sci Rep, 2021 Nov 23;11(1):22791.
PMID: 34815427 DOI: 10.1038/s41598-021-01411-2

The stability and high yielding of Vigna subterranea L. Verdc. genotype is an important factor for long-term development and food security. The effects of G × E interaction on yield stability in 30 Bambara groundnut genotypes in four different Malaysian environments were investigated in this research. The experiment used a randomized complete block design with three replications in each environment. Over multiple harvests, yield component traits such as the total number of pods per plant, fresh pods weight (g), hundred seeds weight (g), and yield per hectare were evaluated in the main and off-season in 2020 and 2021. Stability tests for multivariate stability parameters were performed based on analyses of variance. For all the traits, the pooled analysis of variance revealed highly significant (p

Matched MeSH terms: Principal Component Analysis/methods*
Fulltext Accuracy Improvement for Predicting Parkinson's Disease Progression

Nilashi M, Ibrahim O, Ahani A

Sci Rep, 2016 Sep 30;6:34181.
PMID: 27686748 DOI: 10.1038/srep34181

Parkinson's disease (PD) is a member of a larger group of neuromotor diseases marked by the progressive death of dopamineproducing cells in the brain. Providing computational tools for Parkinson disease using a set of data that contains medical information is very desirable for alleviating the symptoms that can help the amount of people who want to discover the risk of disease at an early stage. This paper proposes a new hybrid intelligent system for the prediction of PD progression using noise removal, clustering and prediction methods. Principal Component Analysis (PCA) and Expectation Maximization (EM) are respectively employed to address the multi-collinearity problems in the experimental datasets and clustering the data. We then apply Adaptive Neuro-Fuzzy Inference System (ANFIS) and Support Vector Regression (SVR) for prediction of PD progression. Experimental results on public Parkinson's datasets show that the proposed method remarkably improves the accuracy of prediction of PD progression. The hybrid intelligent system can assist medical practitioners in the healthcare practice for early detection of Parkinson disease.

Matched MeSH terms: Principal Component Analysis
Fulltext Actinobacteria from Greenwich island and Dee island: isolation, diversity and distribution

Pek, Lim Chu, Chai, Hoon Khoo, Yoke, Kqueen Cheah

Life Sciences, Medicine and Biomedicine, 2017;1(1):1-17.
MyJurnal

Actinobacteria from underexplored and unusual environments have gained significant attention for their capability in producing novel bioactive molecules of diverse chemical entities. Streptomyces is the most prolific Actinobacteria in producing useful molecules. Rapid decline effectiveness of existing antibiotics in the treatment of infections are caused by the emergence of multidrug-resistant pathogens. Intensive efforts are urgently required in isolating non-Streptomyces or rare Actinobacteria and understanding of their distribution in the harsh environment for new drug discovery. In this study, pretreatment of soil samples with 1.5% phenol was used for the selective isolation of Actinobacteria from Dee Island and Greenwich Island. A high number of non-Streptomyces (69.4%) or rare Actinobacteria was significantly recovered despite the Streptomyces (30.6%), including the genera Micromonospora, Micrococcus, Kocuria, Dermacoccus, Brachybacterium, Brevibacterium, Rhodococcus, Microbacterium and Rothia. Reduced diversity and shift of distribution were observed at the elevated level of soil pH. The members of genera Streptomyces, Micromonospora and Micrococcus were found to distribute and tolerate to a relatively high pH level of soil (pH 9.4-9.5), and could potentially be alkaliphilic Actinobacteria. The phylogenetic analysis had revealed some potentially new taxa members of the genera Micromonospora, Micrococcus and Rhodococcus. Principal Component Analysis of soil samples was used to uncover the factors that underlie the diversity of culturable Actinobacteria. Water availability in soil was examined as the principal factor that shaped the diversity of the Actinobacteria, by providing a dynamic source for microbial interactions and elevated diversity of Actinobacteria.

Matched MeSH terms: Principal Component Analysis
Adaptive template matching of photoplethysmogram pulses to detect motion artefact

Lim PK, Ng SC, Lovell NH, Yu YP, Tan MP, McCombie D, et al.

Physiol Meas, 2018 10 11;39(10):105005.
PMID: 30183675 DOI: 10.1088/1361-6579/aadf1e

OBJECTIVE: The photoplethysmography (PPG) signal, commonly used in the healthcare settings, is easily affected by movement artefact leading to errors in the extracted heart rate and SpO2 estimates. This study aims to develop an online artefact detection system based on adaptive (dynamic) template matching, suitable for continuous PPG monitoring during daily living activities or in the intensive care units (ICUs).
APPROACH: Several master templates are initially generated by applying principal component analysis to data obtained from the PhysioNet MIMIC II database. The master template is then updated with each incoming clean PPG pulse. The correlation coefficient is used to classify the PPG pulse into either good or bad quality categories. The performance of our algorithm was evaluated using data obtained from two different sources: (i) our own data collected from 19 healthy subjects using the wearable Sotera Visi Mobile system (Sotera Wireless Inc.) as they performed various movement types; and (ii) ICU data provided by the PhysioNet MIMIC II database. The developed algorithm was evaluated against a manually annotated 'gold standard' (GS).
MAIN RESULTS: Our algorithm achieved an overall accuracy of 91.5% ± 2.9%, with a sensitivity of 94.1% ± 2.7% and a specificity of 89.7% ± 5.1%, when tested on our own data. When applying the algorithm to data from the PhysioNet MIMIC II database, it achieved an accuracy of 98.0%, with a sensitivity and specificity of 99.0% and 96.1%, respectively.
SIGNIFICANCE: The proposed method is simple and robust against individual variations in the PPG characteristics, thus making it suitable for a diverse range of datasets. Integration of the proposed artefact detection technique into remote monitoring devices could enhance reliability of the PPG-derived physiological parameters.

Matched MeSH terms: Principal Component Analysis
Fulltext Algorithm for rapid identification of flavonoids classes

Noh, C.H.C., Azmin, N.F.M., Amid, A., Asnawi, A.L.

International Food Research Journal, 2017;24(101):0-0.
MyJurnal

Bioactive compounds are one of the natural products used especially for medicinal, pharmaceutical and food application. Increasing research performed on the extraction, isolation and identification of bioactive compounds, however non to date has explored on the identification of flavonoids classes. Therefore, this study was focused on the development of algorithm for rapid identification of flavonoids classes which are flavanone, flavone and flavonol and also their derivatives. Fourier Transform Infrared (FTIR) spectroscopy coupled with multivariate statistical data analysis, which is Principal Component Analysis (PCA) was utilized. The results exhibited that few significant wavenumber range provides the identification and characterization of the flavonoids classes based on PCA algorithm. The study concluded that FTIR coupled with PCA analysis can be used as a molecular fingerprint for rapid identification of flavonoids.

Matched MeSH terms: Principal Component Analysis
Fulltext Ambient factors influencing Photovoltaic module temperature in Klang valley

Hedzlin Zainuddin, Maisarah Ismail, Nurul Hidayah Bostamam, Muhamad Mukhzani Muhamad Hanifah, Mohamad Fariz Mohamad Taib, Mohamad Zhafran Hussin

Science Letter, 2016;10(2):23-25.
MyJurnal

The study is conducted to evaluate the significance of solar irradiance, ambient temperature and relative humidity as predictors and to quantify the relative contribution of these ambient parameters as predictors for photovoltaic module temperature model. The module temperature model was developed from experimental data of mono-crystalline and poly-crystalline PV modules retrofitted on metal roof in Klang Valley. The model was developed and analyzed using Multiple Linear Regressions (MLR) and Principle Component Analysis (PCA) Techniques. Solar irradiance, ambient temperature and relative humidity have been proven to be the significant predictors for module temperature. For poly-crystalline PV module, the relative contribution of solar irradiance, ambient temperature and relative humidity are 64.28 %, 17.45 % and 12.64 % respectively. For mono-crystalline PV module, the relative contribution of solar irradiance, ambient temperature and relative humidity are 66.12 %, 17.46 % and 12.48 % respectively. Thus, there is no significant difference in terms of relative contribution of these ambient parameters towards photovoltaic module temperature between poly-crystalline and mono-crystalline PV module technologies.

Matched MeSH terms: Principal Component Analysis
Fulltext Amino Acid and Secondary Metabolite Production in Embryogenic and Non-Embryogenic Callus of Fingerroot Ginger (Boesenbergia rotunda)

Ng TL, Karim R, Tan YS, Teh HF, Danial AD, Ho LS, et al.

PLoS One, 2016;11(6):e0156714.
PMID: 27258536 DOI: 10.1371/journal.pone.0156714

Interest in the medicinal properties of secondary metabolites of Boesenbergia rotunda (fingerroot ginger) has led to investigations into tissue culture of this plant. In this study, we profiled its primary and secondary metabolites, as well as hormones of embryogenic and non-embryogenic (dry and watery) callus and shoot base, Ultra Performance Liquid Chromatography-Mass Spectrometry together with histological characterization. Metabolite profiling showed relatively higher levels of glutamine, arginine and lysine in embryogenic callus than in dry and watery calli, while shoot base tissue showed an intermediate level of primary metabolites. For the five secondary metabolites analyzed (ie. panduratin, pinocembrin, pinostrobin, cardamonin and alpinetin), shoot base had the highest concentrations, followed by watery, dry and embryogenic calli. Furthermore, intracellular auxin levels were found to decrease from dry to watery calli, followed by shoot base and finally embryogenic calli. Our morphological observations showed the presence of fibrils on the cell surface of embryogenic callus while diphenylboric acid 2-aminoethylester staining indicated the presence of flavonoids in both dry and embryogenic calli. Periodic acid-Schiff staining showed that shoot base and dry and embryogenic calli contained starch reserves while none were found in watery callus. This study identified several primary metabolites that could be used as markers of embryogenic cells in B. rotunda, while secondary metabolite analysis indicated that biosynthesis pathways of these important metabolites may not be active in callus and embryogenic tissue.

Matched MeSH terms: Principal Component Analysis
Fulltext An Automated and Intelligent Medical Decision Support System for Brain MRI Scans Classification

Siddiqui MF, Reza AW, Kanesan J

PLoS One, 2015;10(8):e0135875.
PMID: 26280918 DOI: 10.1371/journal.pone.0135875

A wide interest has been observed in the medical health care applications that interpret neuroimaging scans by machine learning systems. This research proposes an intelligent, automatic, accurate, and robust classification technique to classify the human brain magnetic resonance image (MRI) as normal or abnormal, to cater down the human error during identifying the diseases in brain MRIs. In this study, fast discrete wavelet transform (DWT), principal component analysis (PCA), and least squares support vector machine (LS-SVM) are used as basic components. Firstly, fast DWT is employed to extract the salient features of brain MRI, followed by PCA, which reduces the dimensions of the features. These reduced feature vectors also shrink the memory storage consumption by 99.5%. At last, an advanced classification technique based on LS-SVM is applied to brain MR image classification using reduced features. For improving the efficiency, LS-SVM is used with non-linear radial basis function (RBF) kernel. The proposed algorithm intelligently determines the optimized values of the hyper-parameters of the RBF kernel and also applied k-fold stratified cross validation to enhance the generalization of the system. The method was tested by 340 patients' benchmark datasets of T1-weighted and T2-weighted scans. From the analysis of experimental results and performance comparisons, it is observed that the proposed medical decision support system outperformed all other modern classifiers and achieves 100% accuracy rate (specificity/sensitivity 100%/100%). Furthermore, in terms of computation time, the proposed technique is significantly faster than the recent well-known methods, and it improves the efficiency by 71%, 3%, and 4% on feature extraction stage, feature reduction stage, and classification stage, respectively. These results indicate that the proposed well-trained machine learning system has the potential to make accurate predictions about brain abnormalities from the individual subjects, therefore, it can be used as a significant tool in clinical practice.

Matched MeSH terms: Principal Component Analysis/methods
Fulltext An electronic nose for reliable measurement and correct classification of beverages

Mamat M, Samad SA, Hannan MA

Sensors (Basel), 2011;11(6):6435-53.
PMID: 22163964 DOI: 10.3390/s110606435

This paper reports the design of an electronic nose (E-nose) prototype for reliable measurement and correct classification of beverages. The prototype was developed and fabricated in the laboratory using commercially available metal oxide gas sensors and a temperature sensor. The repeatability, reproducibility and discriminative ability of the developed E-nose prototype were tested on odors emanating from different beverages such as blackcurrant juice, mango juice and orange juice, respectively. Repeated measurements of three beverages showed very high correlation (r > 0.97) between the same beverages to verify the repeatability. The prototype also produced highly correlated patterns (r > 0.97) in the measurement of beverages using different sensor batches to verify its reproducibility. The E-nose prototype also possessed good discriminative ability whereby it was able to produce different patterns for different beverages, different milk heat treatments (ultra high temperature, pasteurization) and fresh and spoiled milks. The discriminative ability of the E-nose was evaluated using Principal Component Analysis and a Multi Layer Perception Neural Network, with both methods showing good classification results.

Matched MeSH terms: Principal Component Analysis
Analysis of the genetic diversity of physic nut, Jatropha curcas L. accessions using RAPD markers

Rafii MY, Shabanimofrad M, Puteri Edaroyati MW, Latif MA

Mol Biol Rep, 2012 Jun;39(6):6505-11.
PMID: 22307785 DOI: 10.1007/s11033-012-1478-2

A sum of 48 accessions of physic nut, Jatropha curcas L. were analyzed to determine the genetic diversity and association between geographical origin using RAPD-PCR markers. Eight primers generated a total of 92 fragments with an average of 11.5 amplicons per primer. Polymorphism percentages of J. curcas accessions for Selangor, Kelantan, and Terengganu states were 80.4, 50.0, and 58.7%, respectively, with an average of 63.04%. Jaccard's genetic similarity co-efficient indicated the high level of genetic variation among the accessions which ranged between 0.06 and 0.81. According to UPGMA dendrogram, 48 J. curcas accessions were grouped into four major clusters at coefficient level 0.3 and accessions from same and near states or regions were found to be grouped together according to their geographical origin. Coefficient of genetic differentiation (G(st)) value of J. curcas revealed that it is an outcrossing species.

Matched MeSH terms: Principal Component Analysis
Analysis of the genetic structure of the Malay population: Ancestry-informative marker SNPs in the Malay of Peninsular Malaysia

Yahya P, Sulong S, Harun A, Wan Isa H, Ab Rajab NS, Wangkumhang P, et al.

Forensic Sci Int Genet, 2017 09;30:152-159.
PMID: 28743033 DOI: 10.1016/j.fsigen.2017.07.005

Malay, the main ethnic group in Peninsular Malaysia, is represented by various sub-ethnic groups such as Melayu Banjar, Melayu Bugis, Melayu Champa, Melayu Java, Melayu Kedah Melayu Kelantan, Melayu Minang and Melayu Patani. Using data retrieved from the MyHVP (Malaysian Human Variome Project) database, a total of 135 individuals from these sub-ethnic groups were profiled using the Affymetrix GeneChip Mapping Xba 50-K single nucleotide polymorphism (SNP) array to identify SNPs that were ancestry-informative markers (AIMs) for Malays of Peninsular Malaysia. Prior to selecting the AIMs, the genetic structure of Malays was explored with reference to 11 other populations obtained from the Pan-Asian SNP Consortium database using principal component analysis (PCA) and ADMIXTURE. Iterative pruning principal component analysis (ipPCA) was further used to identify sub-groups of Malays. Subsequently, we constructed an AIMs panel for Malays using the informativeness for assignment (In) of genetic markers, and the K-nearest neighbor classifier (KNN) was used to teach the classification models. A model of 250 SNPs ranked by In, correctly classified Malay individuals with an accuracy of up to 90%. The identified panel of SNPs could be utilized as a panel of AIMs to ascertain the specific ancestry of Malays, which may be useful in disease association studies, biomedical research or forensic investigation purposes.

Matched MeSH terms: Principal Component Analysis
Ancestry-informative marker (AIM) SNP panel for the Malay population

Yahya P, Sulong S, Harun A, Wangkumhang P, Wilantho A, Ngamphiw C, et al.

Int J Legal Med, 2020 Jan;134(1):123-134.
PMID: 31760471 DOI: 10.1007/s00414-019-02184-0

Ancestry-informative markers (AIMs) can be used to infer the ancestry of an individual to minimize the inaccuracy of self-reported ethnicity in biomedical research. In this study, we describe three methods for selecting AIM SNPs for the Malay population (Malay AIM panel) using different approaches based on pairwise FST, informativeness for assignment (In), and PCA-correlated SNPs (PCAIMs). These Malay AIM panels were extracted from genotype data stored in SNP arrays hosted by the Malaysian node of the Human Variome Project (MyHVP) and the Singapore Genome Variation Project (SGVP). In particular, genotype data from a total of 165 Malay individuals were analyzed, comprising data on 117 individual genotypes from the Affymetrix SNP-6 SNP array platform and data on 48 individual genotypes from the OMNI 2.5 Illumina SNP array platform. The HapMap phase 3 database (1397 individuals from 11 populations) was used as a reference for comparison with the Malay genotype data. The accuracy of each resulting Malay AIM panel was evaluated using a machine learning "ancestry-predictive model" constructed by using WEKA, a comprehensive machine learning platform written in Java. A total of 1250 SNPs were finally selected, which successfully identified Malay individuals from other world populations with an accuracy of 90%, but the accuracy decreased to 80% using 157 SNPs according to the pairwise FST method, while a panel of 200 SNPs selected using In and PCAIMs could be used to identify Malay individuals with an accuracy of approximately 80%.

Matched MeSH terms: Principal Component Analysis
Application of third molar development and eruption models in estimating dental age in Malay sub-adults

Mohd Yusof MY, Cauwels R, Deschepper E, Martens L

J Forensic Leg Med, 2015 Aug;34:40-4.
PMID: 26165657 DOI: 10.1016/j.jflm.2015.05.004

The third molar development (TMD) has been widely utilized as one of the radiographic method for dental age estimation. By using the same radiograph of the same individual, third molar eruption (TME) information can be incorporated to the TMD regression model. This study aims to evaluate the performance of dental age estimation in individual method models and the combined model (TMD and TME) based on the classic regressions of multiple linear and principal component analysis. A sample of 705 digital panoramic radiographs of Malay sub-adults aged between 14.1 and 23.8 years was collected. The techniques described by Gleiser and Hunt (modified by Kohler) and Olze were employed to stage the TMD and TME, respectively. The data was divided to develop three respective models based on the two regressions of multiple linear and principal component analysis. The trained models were then validated on the test sample and the accuracy of age prediction was compared between each model. The coefficient of determination (R²) and root mean square error (RMSE) were calculated. In both genders, adjusted R² yielded an increment in the linear regressions of combined model as compared to the individual models. The overall decrease in RMSE was detected in combined model as compared to TMD (0.03-0.06) and TME (0.2-0.8). In principal component regression, low value of adjusted R(2) and high RMSE except in male were exhibited in combined model. Dental age estimation is better predicted using combined model in multiple linear regression models.

Matched MeSH terms: Principal Component 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: Principal Component Analysis
Arrhythmia recognition and classification using combined linear and nonlinear features of ECG signals

Elhaj FA, Salim N, Harris AR, Swee TT, Ahmed T

Comput Methods Programs Biomed, 2016 Apr;127:52-63.
PMID: 27000289 DOI: 10.1016/j.cmpb.2015.12.024

Arrhythmia is a cardiac condition caused by abnormal electrical activity of the heart, and an electrocardiogram (ECG) is the non-invasive method used to detect arrhythmias or heart abnormalities. Due to the presence of noise, the non-stationary nature of the ECG signal (i.e. the changing morphology of the ECG signal with respect to time) and the irregularity of the heartbeat, physicians face difficulties in the diagnosis of arrhythmias. The computer-aided analysis of ECG results assists physicians to detect cardiovascular diseases. The development of many existing arrhythmia systems has depended on the findings from linear experiments on ECG data which achieve high performance on noise-free data. However, nonlinear experiments characterize the ECG signal more effectively sense, extract hidden information in the ECG signal, and achieve good performance under noisy conditions. This paper investigates the representation ability of linear and nonlinear features and proposes a combination of such features in order to improve the classification of ECG data. In this study, five types of beat classes of arrhythmia as recommended by the Association for Advancement of Medical Instrumentation are analyzed: non-ectopic beats (N), supra-ventricular ectopic beats (S), ventricular ectopic beats (V), fusion beats (F) and unclassifiable and paced beats (U). The characterization ability of nonlinear features such as high order statistics and cumulants and nonlinear feature reduction methods such as independent component analysis are combined with linear features, namely, the principal component analysis of discrete wavelet transform coefficients. The features are tested for their ability to differentiate different classes of data using different classifiers, namely, the support vector machine and neural network methods with tenfold cross-validation. Our proposed method is able to classify the N, S, V, F and U arrhythmia classes with high accuracy (98.91%) using a combined support vector machine and radial basis function method.

Matched MeSH terms: Principal Component Analysis

Filters

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

External Links