Method Of Discriminant Function Analysis Research Articles

School–Age Talent Identification in Female Handball by a Mathematical Model: Equation Proposed from Anthropometry, Maturity Offset, Fitness and Technical Field-Tests

ABSTRACT The present study aimed to identify parameters that best discriminate between high-level and scholar-level players for the Brazilian 13–14-year-old girl’s handball and propose a mathematical model to identify sports talent for handball. The sample was made up of all available handball players comprising these two groups: 100 girls who participated in the high-level handball championship in Brazil and 53 girls (age 13–14 years) as finalists of the school-level games in one region of Brazil. We assess the anthropometric profile, maturity offset, physical fitness, and technical skills for handball. To propose the equation, the Discriminant Function Analysis method was used. The discriminant function was significant (p ≤ .05), had a good canonical correlation (0.590), and still had an average Wilk Lambda (0.652). The variables considered in the talent identification model included: 1. flexibility, 2. abdominal strength, 3. lower limbs muscle power, 4. agility, 5. defensive movement and 6. slalom with ball. The values from the equation for identifying school-age athletes with high motor skills and performance for handball can be classified by a cutoff point (Y = 0.192). The results showed that the mathematical-model obtained was able to select school-age athletes with high motor skills for handball, and with the profile for participation in high-level championships.

Pre Harvest Forecasting of Kharif Rice Yield Using Weather Parameters for Strategic Decision Making in Agriculture

In the recent year, pre harvest crop yield forecasting has been a topic of interest for producers, policy makers, government and agricultural related organizations. Pre harvest crop forecasting is important for national food security. Construction of appropriate yield forecast promotes the output of scenario analyses of crop production at a farm level, which enables suitable tactical and strategic decision making by the farmer. Indeed, considerable benefits apply when seasonal forecasting of crop performance is applied across the whole value chain in crop production. Timely and accurate yield forecast is essential for crop production, marketing, storage and transportation decisions as well as for managing the risk associated with these activities. In present manuscript efforts were made for development of pre harvest forecast models by using different statistical approaches viz. multiple linear regression (MLR), discriminant function analysis and ordinal logistic regression. The study utilized the crop yield data and corresponding weekly weather data of last 30 years (1985-2014). The model development was carried out at 35th and 36th SMW (Standard Meteorological Week) for getting forecast well in advance of actual harvesting of the field crop. The study revealed that method of discriminant function analysis gave best pre harvest forecast as compare to remaining developed models. It was observed high value of Adj. R2= 0.94, low value of RMSE= 164.24 and MAPE= 5.30. The model can be used in different crop for reliable and dependable forecast and these forecasts have significant value in agricultural planning and policy making.

Possibilities for predicting preeclampsia development in pregnant women with bronchial asthma

Hypothesis/aims of study. Currently, preeclampsia is one of the most pressing problems of obstetrics due to the complexity of pathogenesis and to the lack of early and reliable diagnostic criteria. The preeclampsia rate in patients with bronchial asthma is proved higher than in asthma free pregnant women. This study aimed to establish the prediction algorithm of preeclampsia development in in pregnant women suffering from bronchial asthma of varying severity and different level of control.
 Study design, materials and methods. Asthma duration was studied in 110 pregnant women using the SPSS Discriminant Function Analysis method. Basic therapy and level of asthma control were studied together with respiratory tests, obstetrician medical history, and complications of the first and second trimesters of pregnancy. In addition, serum interleukin panel was assessed and placental Doppler measurement was carried out.
 Results. Clinical and statistical analysis made it possible out of 87 significant risk factors for the development of hypertensive disorders and preeclampsia to form a highly informative set of signs for a linear discriminant model for predicting preeclampsia: 1) asthma exacerbation in the first trimester of pregnancy; 2) asthma duration severity; 3) average dose of inhaled glucocorticosteroid drugs administered to the exact patient during pregnancy; 4) serum levels of tumor necrosis factor, interferon gamma, and interleukins-4, 6, and 8.
 Conclusion. The inclusion method of step-by-step discriminant analysis allowed establishing a highly informative four-component complex of clinical predictors for preeclampsia development in pregnant women with asthma. The results of the model testing showed its extremely high reliability (up to 100% within study selection as well as within control selection). Thus, the study results can be recommended for clinical use.

Correlation between in vitro and in vivo antimalarial activity of compounds using CQ-sensitive and CQ-resistant strains of Plasmodium falciparum and CQ-resistant strain of P. yoelii.

Present efforts have been made to establish a correlation between in vitro and in vivo antimalarial activity using MIC, IC50 and IC90 values against CQ-sensitive (3D7) and CQ-resistant (K1) strains of Plasmodium falciparum and in vivo activity against Plasmodium yoelii. The method of discriminant function analysis (DFA) was applied to analyze the data. It was observed that in vitro IC90 values against both 3D7 and K1 strains (p<0.001) have strong correlation with in vivo curative activity. The respective IC50 and IC90 values of compounds, which cured mice (i.e., animals did not show recrudescence of parasitemia even after 60days posttreatment), ranged between 3 and 14nM and 14 and 186nM against 3D7 and between 9 and 65nM and 24 and 359nM against the K1 strain of P. falciparum. Whereas the IC50 and IC90 values of compounds which exhibited in vivo suppressive activity in mice ranged between 10 and 307nm and 61 and >965nM, respectively, against 3D7 and 75 and >806nm and 241 and >1232nM against the K1 strain of P. falciparum. The findings suggest that IC90 values against both 3D7 and K1 strains (p<0.02) are the main contributors for the prediction of in vivo curative activity of a new molecule. Apart from this, a reasonable correlation between MIC and IC50 values of compounds has also been established.

Mineralogical discrimination of the pleistocene loess/paleosol sections in Srijem and Baranja, Croatia

Abstract Previous investigations of the mineralogical composition of loess sections (loess, loess-like sediments, paleosols, alluvial intercalations) in the Carpathian Basin have concluded that the Danube River is the dominant control on the loessitic parent material. These investigations also identify a significant role for the Danube’s tributaries in creating local variations. The north–south alignment of these sections forms a transect from the central part of the Carpathian Basin to its southern edge. In this work, the mineral origin of loess sediments was identified by using the multivariate statistical method of discriminant function analysis. Two models were constructed based on the modal composition as the suite of predictor (independent) variables: one is using geographic location as the a priori grouping criterion (SECTION); another employing the difference between the sampling media (LITHOLOGY). Both of the examined discriminant models demonstrate the existence of the mixing zones. The Erdut section is a clear mixture of the mineralogies at the other studied locations, while loesses appear generally intermediate in mineralogy between alluvium and paleosol. The main rationale for the observed difference in modal composition between the Sarengrad and other analyzed sections is the proximity of the Sarengrad section to the Sava River floodplain and Dinaric Ophiolite Zone (DOZ), both important source areas for aeolian sediments in the southern edge of the Carpathian Basin that transport material from the Central Bosnian Mountains unit of DOZ. Chemically, the most resistant heavy minerals together with opaque minerals are exclusively associated with paleosols, being typical products of geochemical pedogenic processes.

Discrimination of patients with diabetes mellitus and healthy subjects based on laser-induced breakdown spectroscopy of their fingernails

Laser-induced breakdown spectroscopy (LIBS) is applied to investigate the effect of diabetes mellitus (DM) on the elemental composition of fingernails. Measurements are carried out on 85 fingernail clippings including 51 diabetic and 34 control subjects. An auto-focus system has been designed and used in experiments to improve the repeatability of LIBS measurements. Classification of diabetic and nondiabetic subjects is examined using discriminant function analysis (DFA) method. This classification is based on 82 atomic, ionic, and molecular emission lines belonging to 13 elements as well as one molecule of fingernails. Emission lines that can be used as the best predictors are identified. The possibility of using this method for screening purposes is discussed based on the classification results. This preliminary work shows the ability of LIBS of fingernails in discrimination of DM patients and nondiabetic subjects using DFA method and its feasibility in screening purposes.

전자코를 이용한 다양한 유형의 치즈 제품 풍미성분 분석

The objective of this study was to analyze the flavor pattern of different varieties of cheeses. Four of the each following cheese varieties such as shred type pizza cheese, Cheddar cheese, Mozzarella block cheese, and white mold-ripened cheeses, stored at 4 o C during 2 wks were examined before and after cooking at 70 o C and 160 o C. Flavor patterns of these cheeses were analyzed using an electronic nose system based on mass spectrometer. All data were treated by multivariate data processing based on discriminant function analysis (DFA). The results showed the discriminant model by DFA method. Data revealed that flavor patterns of pizza cheeses were well separated as storage prolonged and obviously discriminated as the higher the cooking temperature. The result of pattern recognition analysis based on discriminant function analysis showed that new brand of pizza cheese produced by Imsil Cheese Cooperative was located at middle between the flavors of the imported brands of pizza cheese and those of domestic brand of pizza cheeses. Imsil cheese has a unique flavor pattern among other variety of cheeses. Application of pattern recognition analysis by electronic nose might be useful and advanced technology for characterizing in flavor pattern of cheese products from different origins and different categories of cheeses.

Discrimination of polymers by laser induced breakdown spectroscopy together with the DFA method

Laser Induced Breakdown Spectroscopy (LIBS) is used to analyze and identify six kinds of the most important recyclable polymers i.e high density polyethylene (HDPE), low density polyethylene (LDPE), polyethylene terephthalate (PET), polypropylene (PP), polystyrene (PS) and polyvinyl chloride (PVC). Using a Nd:YAG laser with wavelength 1064, a plasma is created on the polymer surface. By analysis of spectral emission of plasma, some qualitative information about the plasma elements is obtained. The plasma spectra of polymers are similar and contain strong carbon and hydrogen spectral lines. Here, a statistical method called discriminant function analysis (DFA) is used to discriminate between the polymers by slight differences between the spectra. DFA establishes a model on the basis of input variables to predict group memberships of polymers. The spectral line ratios of C, CN, C2, N Cl, O and H are used as input variables in DFA. Results show that LIBS together with DFA has the ability to correctly classify 99% of the polymers.

Metric method for sex determination based on the 12th thoracic vertebra in contemporary north-easterners in China

Many studies have shown that discriminant function equations, used in the determination of sex from skeletons, are population specific. The aim of the present research was to develop discriminant function equations for sex determination using the 12th thoracic vertebra (T12) in a contemporary northeast Chinese sample and to investigate whether the differences of the T12 between males and females consist more in shape than in size. Thirty linear measurements were obtained from 141 three-dimensional reconstructed T12 models (78 males and 63 females), and then 112 ratios were calculated by using the thirty linear measurements. Of the 30 linear measurements, 28 were sexually dimorphic, and their univariate discriminant function equations predicted sex with 56.4–90.1% accuracies. Of the 112 ratios, 62 were sexually dimorphic, with accuracies ranging from 56.7% to 73.8%. Using stepwise method of discriminant function analysis, four variables predicted sex with 94.2% accuracy. It is concluded that the T12 vertebra of the north-easterners in China is useful for sex determination, and the size of the T12 vertebra contributes more than the shape in the differences of the T12 vertebra between males and females.

Sex assessment using measurements of the first lumbar vertebra

Sex determination is a vital part of the medico-legal system but can be difficult in cases where the integrity of the body has been compromised. The purpose of this study was to develop a technique for sex assessment from measurements of the first lumber vertebrate. Twenty-nine linear measurements and five ratios were collected from 113 Chinese adult males and 97 Chinese adult females using digital three-dimensional anthropometry methods. By using discriminant analysis, we found that 23 linear measurements and two ratios identified sexual dimorphism (P<0.01), with predictive accuracy ranging from 57.1% to 86.6%. Using a stepwise method of discriminant function analysis, we found three dimensions predicted sex with 88.6% accuracy: (a) upper end-plate width (EPWu), (b) left pedicle height (PHl), and (c) middle end-plate depth (EPDm). This study shows that a single first lumber vertebra can be used for this purpose, and that the discriminant equation will help forensic determination of sex in the Chinese population.

Determination of Sex for the 12th Thoracic Vertebra by Morphometry of Three‐dimensional Reconstructed Vertebral Models

Thirty-three linear measurements and two ratios were derived from 102 12th thoracic vertebrae of the Digital Korean database at the Catholic Institute for Applied Anatomy. Of 35 linear traits, 23 were sexually dimorphic. We created 23 discriminant function equations that predicted sex with 62.7-85.3% accuracy. The analysis using combinations of two factors gave higher accuracies: most equations with accuracies over 80% included at least one measurement involving the coronal diameter of the vertebral endplate. Using stepwise method of discriminant function analysis, three variables predicted sex with 90.0% accuracy: the coronal diameter of the superior endplate of the vertebral body, the ratio of anterior to middle height of the body, and the length of the left mammillary process and pedicle. Coronal dimensions of the vertebral body represented the major sex difference. These equations will help forensic discrimination of the sex of this vertebra among Koreans.

산란계의 열환경별 특이음에 대한 음성학적 분석

본 연구는 산란계가 적정 환경, 더운 환경 그리고 추운 환경에서 특이하게 내는 특이음을 분류한 후 이들을 음성학적으로 판별할 수 있는지를 규명하고자 수행되었다. 일반 발성음은 총 5가지 형태, 더위stress 특이음은 1가지 형태, 그리고 추위stress 특이음은 총 3가지 형태로 각각 나타났다. 기본주파수, 음의 강도, 음의 길이 및 포먼트에 대하여 열환경별 발성음간 유의차를 분석한 결과 모든 parameter에서 유의차가 인정되었으나, Discriminant 분석을 실시하였을 때 음의 길이, 제 1포먼트, 제 3포먼트 및 제 4포먼트가 다른 parameter들 보다 유용한 parameter로 나타났다. 이상의 결과들을 종합해 볼 때, 산란계는 열환경 변화에 따라 특이음을 내었으며, 이들 특이음은 기본주파수, 음의 강도, 음의 길이 및 포먼트 등과 같은 parameter들에 의하여 음성학적으로 판별될 수 있었다. The aim of this study was to divide vocalizations of laying hens (Hy-Line Brown) into general vocalizations (GVs), heat stress-related vocalization (HSV), and cold stress-related vocalizations (CSVs) and to determine if they are classified by the discriminant function analysis method. Thirty laying hens, 65-wk-old, were recorded using digital video recorders 2 times from 10:00 to 14:00 h in each thermal environment (thermoneutral: <TEX>$22.0{\pm}1.8^{\circ}C$</TEX>, too hot: <TEX>$32.0{\pm}2.0^{\circ}C$</TEX>, too cold: <TEx>$8.0{\pm}1.9^{\circ}C)$</TEX> after a 7 day acclimation period. When the laying hens were not recorded, they were kept in thermoneutral conditions. The GVs, HSV, and CSVs were divided based on the shapes of spectrums and spectrograms. The GVs, HSV, and CSVs were identified as 5, 1, and 3 types, respectively. Pitch, intensity, duration, formant 1, formant 2, formant 3, and formant 4 among the thermal environment-related vocalizations were significantly different (P<0.001). The discrimination rate determined by discriminant function analysis was 86.2%. These results suggest that HSV and CSVs are present and may be used as an indicator of the thermal environment.

Progress toward the Rapid Nondestructive Assessment of the Floral Origin of European Honey Using Dispersive Raman Spectroscopy

Raman spectroscopy was investigated for its ability to discriminate between honey samples from different floral and geographical origins. The major vibrational modes in the Stokes Raman spectra were assigned and could be attributed to the four main sugars found in the honeys. The chemometric clustering method of discriminant function analysis indicated that the major differences between the honeys was due to their botanical origin rather than their country of origin, and this was confirmed by artificial neural network analyses. We consider the noninvasive nondestructive analysis of honey by Raman spectroscopy to be an alternative to the laborious and highly specialized mellisopalynology typing method currently used to identify the floral origin of honey.

Histological discrimination of malignancy in mucinous ovarian tumours

Eight histological features were measured quantitatively in a group of 77 ovarian mucinous carcinomas and a group of 28 benign mucinous cystomas. These were compared with the duration of survival of the patients and the clinical staging of the tumours. Using the method of discriminant function analysis it was possible to identify a group of tumours of 'borderline malignancy'. Although single histological features were inadequate indicators of prognosis a combination of three features proved fairly accurate.

On the method of discriminant function analysis for sex determination of the skull

Discriminant functions for sex determination calculated from the Westerhus series were applied to temporaly and spatially different skeletal material. The misclassifications and the different methods of approximating the sectioning point were discussed.

7—The Relation of Grade to the Physical Properties of Retted Flax Fibre

The traditional technique of hand-hackling has been adapted and standardised to give a uniform product on which measurements of physical properties of the fibre can be made. The expert assessment of grade of scutched flax has been correlated with the physical properties of the fibre; the Grade Index, where L is the mean strand length and ρ the over-all density of scutched flax, and A the mean cross-sectional area and F the ½-in. tuft strength of hand-hackled line, is proportional to the judged grade. The fibre type, denoted by the sub marks, c, d, and t, can be estimated from the product AL. The statistical methods of regression analysis and discriminant functions, each involving seven independent variables, did not improve the estimate of grade or fibre type beyond that given by the above empirical formulae.An outline of the method of discriminant function analysis is given in an appendix.