The conventional method of grading Harumanis mango is time-consuming, costly and affected by human bias. In this research, an in-line system was developed to classify Harumanis mango using computer vision. The system was able to identify the irregularity of mango shape and its estimated mass. A group of images of mangoes of different size and shape was used as database set. Some important features such as length, height, centroid and parameter were extracted from each image. Fourier descriptor and size-shape parameters were used to describe the mango shape while the disk method was used to estimate the mass of the mango. Four features have been selected by stepwise discriminant analysis which was effective in sorting regular and misshapen mango. The volume from water displacement method was compared with the volume estimated by image processing using paired t-test and Bland-Altman method. The result between both measurements was not significantly different (P > 0.05). The average correct classification for shape classification was 98% for a training set composed of 180 mangoes. The data was validated with another testing set consist of 140 mangoes which have the success rate of 92%. The same set was used for evaluating the performance of mass estimation. The average success rate of the classification for grading based on its mass was 94%. The results indicate that the in-line sorting system using machine vision has a great potential in automatic fruit sorting according to its shape and mass.
Callus was induced from mangosteen (Garcinia mangostana L.) young purple-red leaves on Murashige and Skoog basal medium with various combinations of plant growth regulators. Murashige and Skoog medium with 4.44 µM 6-benzylaminopurine and 4.52 µM 2,4-dichlorophenoxyacetic acid was the best for friable callus induction. This friable callus was used for the initiation of cell suspension culture. The effects of different combinations of 6-benzylaminopurine and 2,4-dichlorophenoxyacetic acid, carbon sources and inoculum sizes were tested. It was found that combination of 2.22 µM 6-benzylaminopurine + 2.26 µM 2,4-dichlorophenoxyacetic acid, glucose (30 g/l) and 1.5 g/50 ml inoculum size was the best for cell growth. Callus and cell suspension cultures were then treated either with 100 µM methyl jasmonate as an elicitor for 5 days, or 0.5 g/l casein hydrolysate as an organic supplement for 7 days. Metabolites were then extracted and profiled using liquid chromatography-time of flight mass spectrometry. Multivariate discriminant analyses revealed significant metabolite differences (P ≤ 0.05) for callus and suspension cells treated either with methyl jasmonate or casein hydrolysate. Based on MS/MS data, methyl jasmonate stimulated the production of an alkaloid (thalsimine) and fatty acid (phosphatidyl ethanolamine) in suspension cells while in callus, an alkaloid (thiacremonone) and glucosinolate (7-methylthioheptanaldoxime) was produced. Meanwhile casein hydrolysate stimulated the production of alkaloids such as 3ß,6ß-dihydroxynortropane and cis-hinokiresinol and triterpenoids such as schidigerasaponin and talinumoside in suspension cells. This study provides evidence on the potential of secondary metabolite production from in vitro culture of mangosteen.
Dioscorea oppositifolia is an important crop and functional food. D. oppositifolia tuber is often adulterated with D. persimilis, D. alata, and D. fordii tuber in the commercial market. This study proposed an integrated Fourier transform infrared spectroscopy (FT-IR) with chemometric approach to differentiate these four Dioscorea species. A total of 107 Dioscorea spp. tuber samples were collected from different locations in China. Principal Component Analysis (PCA), PCA-Class, and Orthogonal Partial Least Square Discriminant Analysis (OPLS-DA) were utilised to classify the FT-IR spectra. In this PCA is unable to differentiate the Dioscorea spp. tuber effectively. However, PCA-Class and OPLS-DA can distinguish spp. these 4 species Dioscorea tuber with high accuracy, sensitivity, and specificity. Additionally, the RMSEE, RMSEP and RMSECV values for OPLS-DA model were low, showing that it is a good model. The combination of FT-IR with the PCA-Class and OPLS-DA is practical in discriminating Dioscorea spp. tubers.
This study investigates the spatial water quality pattern of seven stations located along the main Langat River. Environmetric methods, namely, the hierarchical agglomerative cluster analysis (HACA), the discriminant analysis (DA), the principal component analysis (PCA), and the factor analysis (FA), were used to study the spatial variations of the most significant water quality variables and to determine the origin of pollution sources. Twenty-three water quality parameters were initially selected and analyzed. Three spatial clusters were formed based on HACA. These clusters are designated as downstream of Langat river, middle stream of Langat river, and upstream of Langat River regions. Forward and backward stepwise DA managed to discriminate six and seven water quality variables, respectively, from the original 23 variables. PCA and FA (varimax functionality) were used to investigate the origin of each water quality variable due to land use activities based on the three clustered regions. Seven principal components (PCs) were obtained with 81% total variation for the high-pollution source (HPS) region, while six PCs with 71% and 79% total variances were obtained for the moderate-pollution source (MPS) and low-pollution source (LPS) regions, respectively. The pollution sources for the HPS and MPS are of anthropogenic sources (industrial, municipal waste, and agricultural runoff). For the LPS region, the domestic and agricultural runoffs are the main sources of pollution. From this study, we can conclude that the application of environmetric methods can reveal meaningful information on the spatial variability of a large and complex river water quality data.
The present study deals with the assessment of Langat River water quality with some chemometrics approaches such as cluster and discriminant analysis coupled with an artificial neural network (ANN). The data used in this study were collected from seven monitoring stations under the river water quality monitoring program by the Department of Environment (DOE) from 1995 to 2002. Twenty three physico-chemical parameters were involved in this analysis. Cluster analysis successfully clustered the Langat River into three major clusters, namely high, moderate and less pollution regions. Discriminant analysis identified seven of the most significant parameters which contribute to the high variation of Langat River water quality, namely dissolved oxygen, biological oxygen demand, pH, ammoniacal nitrogen, chlorine, E. coli, and coliform. Discriminant analysis also plays an important role as an input selection parameter for an ANN of spatial prediction (pollution regions). The ANN showed better prediction performance in discriminating the regional area with an excellent percentage of correct classification compared to discriminant analysis. Multivariate analysis, coupled with ANN, is proposed, which could help in decision making and problem solving in the local environment.
Information about the sex of individuals is important for human identification. This study was conducted to quantify classification rates of sex prediction models for Malaysians using odontometric profiles. Mesiodistal (MD) and buccolingual (BL) crown dimensions of the permanent dentition were studied in 400 young adult Malaysians, giving a total of 28 tooth size variables. The sample consisted of three major ethnic groups, the Malays, Chinese and Tamils, since the aim was to assess sex dimorphism in Malaysians as a whole. Results showed that the mesiodistal diameter of the lower canine was the most sexually dimorphic dimension in Malaysian Malays and Tamils. Univariate analyses showed that the magnitude and pattern of sex dimorphism varies between these three ethnic groups, with Malaysian Chinese and Tamils being more dimorphic than the Malaysian Malays. Stepwise discriminant functions were generated bearing in mind their application in practical forensic situations. The range of classification rates was from 70.2% to 78.5% for the composite Malaysian group, and 83.8%, 77.9%, 72.4% for Malaysian Chinese, Malays and Tamils, respectively. The 'Area Under the Receiver Operating Characteristic Curve statistics' indicated good classification rates for three prediction models obtained using a combination of all tooth size variables, mandibular teeth, and mesiodistal dimensions in the composite Malaysian group, and for all tooth size variables in each ethnic group. The present study provides strong support for the value of odontometry as an adjunct scientific method for sex prediction in human identification.
A validated screening tool for patient triage based on the pain symptoms, could potentially optimize the resources and expertise available in dental pain management. The aim of this study was to translate and validate the Modified Dental Pain Questionnaire (M-DePaQ) for use in categorizing patients with pain into three groups of common dental conditions. Forward Malay and Chinese translation was performed, followed by backward English translation. The translation was reviewed by an expert panel and pre-tested on patients who are native speakers.Consecutive patients aged 18 years and older experiencing pain and attending the primary dental care clinic completed the questionnaires. Four calibrated dentists made clinical diagnoses independent of the questionnaire responses. For data analysis, the cases were split randomly into Random Sample 1 (RS1) and Random Sample 2 (RS2). Discriminant analysis was performed on RS1 to develop a model for classifying dental pain cases into three groups. The model was applied to cases in RS2, and a cross-validated accuracy rate was obtained. Criterion validity was assessed using measures such as sensitivity, specificity, positive predictive value, and kappa. Of the 234 questionnaires distributed, 216 (92.3%) were returned. Classification rates were recorded at 73.8% for RS1, 75.0% for RS2, and 71.1% for all cases. The sensitivity values were 0.72, 0.39, and 0.43 for Groups 1, 2, and 3, respectively. The corresponding specificity values were 0.42, 0.87, and 0.94. The discriminant validity of the adapted questionnaire was satisfactory, but the criterion validity could not be established because of biases incorporated in the study.
The objective of the study was to determine whether discriminant analysis of characteristics of dyspepsia can differentiate peptic ulcer from non-ulcer dyspepsia in a Malaysian population. Two hundred and twenty six patients with dyspepsia were interviewed using a standard history questionnaire before undergoing upper gastrointestinal endoscopy. Forty seven patients had peptic ulcer while 149 others were classified as having non-ulcer dyspepsia. Stepwise logistic regression analysis was done on 25 variables. The study showed that only five of these variables could differentiate peptic ulcer from non-ulcer dyspepsia, namely, nocturnal pain, pain before meals or when hungry, absence of nausea, age and sex. A scoring system was devised based on these discriminant symptoms. At a sensitivity of 51%, the specificity for peptic ulcer was 83%, but only prospective studies will determine if this scoring system is of actual clinical value.
Partial least squares-discriminant analysis (PLS-DA) is a versatile algorithm that can be used for predictive and descriptive modelling as well as for discriminative variable selection. However, versatility is both a blessing and a curse and the user needs to optimize a wealth of parameters before reaching reliable and valid outcomes. Over the past two decades, PLS-DA has demonstrated great success in modelling high-dimensional datasets for diverse purposes, e.g. product authentication in food analysis, diseases classification in medical diagnosis, and evidence analysis in forensic science. Despite that, in practice, many users have yet to grasp the essence of constructing a valid and reliable PLS-DA model. As the technology progresses, across every discipline, datasets are evolving into a more complex form, i.e. multi-class, imbalanced and colossal. Indeed, the community is welcoming a new era called big data. In this context, the aim of the article is two-fold: (a) to review, outline and describe the contemporary PLS-DA modelling practice strategies, and (b) to critically discuss the respective knowledge gaps that have emerged in response to the present big data era. This work could complement other available reviews or tutorials on PLS-DA, to provide a timely and user-friendly guide to researchers, especially those working in applied research.
In response to our review paper [L. C. Lee et al., Analyst, 2018, 143, 3526-3539], we present a study that compares empirical differences between PLS1-DA and PLS2-DA algorithms in modelling a colossal ATR-FTIR spectral dataset. Over the past two decades, partial least squares-discriminant analysis (PLS-DA) has gained wide acceptance and huge popularity in the field of applied research, partly due to its dimensionality reduction capability and ability to handle multicollinear and correlated variables. To solve a K-class problem (K > 2) using PLS-DA and high-dimensional data like infrared spectra, one can construct either K one-versus-all PLS1-DA models or only one PLS2-DA model. The aim of this work is to explore empirical differences between the two PLS-DA algorithms in modeling a colossal ATR-FTIR spectral dataset. The practical task is to build a prediction model using the imbalanced, high dimensional, colossal and multi-class ATR-FTIR spectra of blue gel pen inks. Four different sub-datasets were prepared from the principal dataset by considering the raw and asymmetric least squares (AsLS) preprocessed forms: (a) Raw-global region; (b) Raw-local region; (c) AsLS-global region; and (d) AsLS-local region. A series of 50 models which includes the first 50 PLS components incrementally was constructed repeatedly using the four sub-datasets. Each model was evaluated using six different variants of v-fold cross validation, autoprediction and external testing methods. As a result, each PLS-DA algorithm was represented by a number of figures of merit. The differences between PLS1-DA and PLS2-DA algorithms were assessed using hypothesis tests with respect to model accuracy, stability and fitting. On the other hand, confusion matrices of the two PLS-DA algorithms were inspected carefully for assessment of model parsimony. Overall, both the algorithms presented satisfactory model accuracy and stability. Nonetheless, PLS1-DA models showed significantly higher accuracy rates than PLS2-DA models, whereas PLS2-DA models seem to be much more stable compared to PLS1-DA models. Eventually, PLS2-DA also proved to be less prone to overfitting and is more parsimonious than PLS1-DA. In conclusion, the relatively high accuracy of the PLS1-DA algorithm is achieved at the cost of rather low parsimony and stability, and with an increased risk of overfitting.
High-fat diet (HFD) interferes with the dietary plan of patients with type 2 diabetes mellitus (T2DM). However, many diabetes patients consume food with higher fat content for a better taste bud experience. In this study, we examined the effect of HFD on rats at the early onset of diabetes and prediabetes by supplementing their feed with palm olein oil to provide a fat content representing 39% of total calorie intake. Urinary profile generated from liquid chromatography-mass spectrometry analysis was used to construct the orthogonal partial least squares discriminant analysis (OPLS-DA) score plots. The data provide insights into the physiological state of an organism. Healthy rats fed with normal chow (NC) and HFD cannot be distinguished by their urinary metabolite profiles, whereas diabetic and prediabetic rats showed a clear separation in OPLS-DA profile between the two diets, indicating a change in their physiological state. Metformin treatment altered the metabolomics profiles of diabetic rats and lowered their blood sugar levels. For prediabetic rats, metformin treatment on both NC- and HFD-fed rats not only reduced their blood sugar levels to normal but also altered the urinary metabolite profile to be more like healthy rats. The use of metformin is therefore beneficial at the prediabetes stage.
Allele frequencies for the nine STRs genetic loci included in the AmpFlSTR Profiler kit were obtained from samples of unrelated individuals comprising 139-156 Malays, 149-153 Chinese and 132-135 Indians, residing in Malaysia.
The study attempts to use multivariate analysis to evaluate the profile of male player for developments of Long-Term Talent in Sports (LT-TiS) model based on anthropometric and motor fitness components. Data of anthropometric and motor fitness included power, flexibility, coordination and speed were obtained from 2019 respondents aged 7.32±0.52 year. Data interpretations were carried out using multivariate analysis of Principle Components Analysis (PCA) and Discriminant analysis (DA). The adequacy of sampling has been measured using Bartletts tests on sphericity and Kaiser-Meyer-Olkin (KMO) has been used, with this conformance of running the Principal Component Analysis (PCA). Then, Discriminant Analysis (DA) were used to validate the correctness of group classification by LT-TiS model. Then, Discriminant Analysis (DA) were used to validate the correctness of group classification by LT-TiS. As a result, two factors with eigenvalues greater than 1 were extracted which accounted for 55.00% of the variations present in the original variables was found. The two factors were used to obtain the factor score coefficients explained by 27.86% and 27.21% of the variations in player performance respectively. Factor 1 revealed high factor loading on motor fitness compared to factor 2 as it was significantly related to anthropometrics. A model was obtained using standardized coefficient of factor 1. Three clusters of performance were shaped in view by categorizing; LT−TiS≥65%, 40%≤LT−TiS
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.
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.
Diabetes mellitus (DM) is a chronic disease that can affect metabolism of glucose and other metabolites. In this study, the normal- and obese-diabetic rats were compared to understand the diabetes disorders of type 1 and 2 diabetes mellitus. This was done by evaluating their urine metabolites using proton nuclear magnetic resonance (1H NMR)-based metabolomics and comparing with controls at different time points, considering the induction periods of obesity and diabetes. The biochemical parameters of the serum were also investigated. The obese-diabetic model was developed by feeding the rats a high-fat diet and inducing diabetic conditions with a low dose of streptozotocin (STZ) (25 mg/kg bw). However, the normal rats were induced by a high dose of STZ (55 mg/kg bw). A partial least squares discriminant analysis (PLS-DA) model showed the biomarkers of both DM types compared to control. The synthesis and degradation of ketone bodies, tricarboxylic (TCA) cycles, and amino acid pathways were the ones most involved in the variation with the highest impact. The diabetic groups also exhibited a noticeable increase in the plasma glucose level and lipid profile disorders compared to the control. There was also an increase in the plasma cholesterol and low-density lipoprotein (LDL) levels and a decline in the high-density lipoprotein (HDL) of diabetic rats. The normal-diabetic rats exhibited the highest effect of all parameters compared to the obese-diabetic rats in the advancement of the DM period. This finding can build a platform to understand the metabolic and biochemical complications of both types of DM and can generate ideas for finding targeted drugs.
This study aims to test the translated Hausa version of the stroke impact scale SIS (3.0) and further evaluate its psychometric properties. The SIS 3.0 was translated from English into Hausa and was tested for its reliability and validity on a stratified random sample adult stroke survivors attending rehabilitation services at stroke referral hospitals in Kano, Nigeria. Psychometric analysis of the Hausa-SIS 3.0 involved face, content, criterion, and construct validity tests as well as internal and test-retest reliability. In reliability analyses, the Cronbach's alpha values for the items in Strength, Hand function, Mobility, ADL/IADL, Memory and thinking, Communication, Emotion, and Social participation domains were 0.80, 0.92, 0.90, 0.78, 0.84, 0.89, 0.58, and 0.74, respectively. There are 8 domains in stroke impact scale 3.0 in confirmatory factory analysis; some of the items in the Hausa-SIS questionnaire have to be dropped due to lack of discriminate validity. In the final analysis, a parsimonious model was obtained with two items per construct for the 8 constructs (Chi-square/df < 3, TLI and CFI > 0.9, and RMSEA < 0.08). Cross validation with 1000 bootstrap samples gave a satisfactory result (P = 0.011). In conclusion, the shorter 16-item Hausa-SIS seems to measure adequately the QOL outcomes in the 8 domains.
Electromyography (EMG) signal is one of the extensively utilised biological signals for predicting human motor intention, which is an essential element in human-robot collaboration platforms. Studies on motion intention prediction from EMG signals have often been concentrated on either classification and regression models of muscle activity. In this study, we leverage the information from the EMG signals, to detect the subject's intentions in generating motion commands for a robot-assisted upper limb rehabilitation platform. The EMG signals are recorded from ten healthy subjects' biceps muscle, and the movements of the upper limb evaluated are voluntary elbow flexion and extension along the sagittal plane. The signals are filtered through a fifth-order Butterworth filter. A number of features were extracted from the filtered signals namely waveform length (WL), mean absolute value (MAV), root mean square (RMS), standard deviation (SD), minimum (MIN) and maximum (MAX). Several different classifiers viz. Linear Discriminant Analysis (LDA), Logistic Regression (LR), Decision Tree (DT), Support Vector Machine (SVM) and k-Nearest Neighbour (k-NN) were investigated on its efficacy to accurately classify the pre-intention and intention classes based on the significant features identified (MIN and MAX) via Extremely Randomised Tree feature selection technique. It was observed from the present investigation that the DT classifier yielded an excellent classification with a classification accuracy of 100%, 99% and 99% on training, testing and validation dataset, respectively based on the identified features. The findings of the present investigation are non-trivial towards facilitating the rehabilitation phase of patients based on their actual capability and hence, would eventually yield a more active participation from them.
In this paper, a Semantic Web service matchmaker called UltiMatch-NL is presented. UltiMatch-NL applies two filters namely Signature-based and Description-based on different abstraction levels of a service profile to achieve more accurate results. More specifically, the proposed filters rely on semantic knowledge to extract the similarity between a given pair of service descriptions. Thus it is a further step towards fully automated Web service discovery via making this process more semantic-aware. In addition, a new technique is proposed to weight and combine the results of different filters of UltiMatch-NL, automatically. Moreover, an innovative approach is introduced to predict the relevance of requests and Web services and eliminate the need for setting a threshold value of similarity. In order to evaluate UltiMatch-NL, the repository of OWLS-TC is used. The performance evaluation based on standard measures from the information retrieval field shows that semantic matching of OWL-S services can be significantly improved by incorporating designed matching filters.
The present study aims to identify the essential technical and tactical performance indicators that could differentiate winning and losing performance in the Asian elite beach soccer competition. A set of 20 technical and tactical performance indicators namely; shot back-third, shot mid-third, shot front-third, pass back-third, pass mid-third, pass front-third, shot in box, shot outbox, chances created, interception, turnover, goals scored 1st period, goals scored 2nd period, goals scored 3rd period, goals scored extra time, tackling, fouls committed, complete save, incomplete save and passing error were observed during the beach soccer Asian Football Confederation tournament 2017 held in Malaysia. A total of 23 matches from 12 teams were notated using StatWatch application in real-time. Discriminant analysis (DA) of standard, backward as well stepwise modes were used to develop a model for the winning (WT) and losing team (LT) whilst Mann-Whitney U test was utilized to ascertain the differences between the WT and LT with respect to the performance indicators evaluated. The standard backward, forward and stepwise discriminates the WT and the LT with an excellent accuracy of 95.65%, 91.30% and 89.13%, respectively. The standard DA model discriminated the teams from seven performance indicators whilst both the backward and forward stepwise identified two performance indicators. The Mann-Whitney U test analysis indicated that the WT is statistically significant from the LT based on the performance indicators determined from the standard mode model of the DA. It was demonstrated that seven performance indicators namely; shot front-third, pass front-third, chances created, goals scores at the 1st period, goals scored at the 2nd period, goals scored at 3rd period were directly linked to a successful performance whilst the incomplete save by the keeper attribute towards the poor performance of the team. The present finding could serve useful to the coaches as well as performance analysts as a measure of profiling successful performance and enables team improvement with respect to the associated performance indicators.