Single Sample Discriminant Analysis Based on Gabor Transform

To solve the small sample problem of biometric identification, this paper investigates the limiting case of the problem, i.e., the recognition of a single training sample, and proposes a single sample discriminant analysis method based on Gabor wavelet and KPCA-RBF (KPRC) classifier (kernel principal component analysis-radial basis function). The proposed method performs pixel-level fusion of face and palmprint images. Firstly, a face image and a palmprint image were subject to two-dimensional (2D) Gabor wavelet transform. The resulting Gabor face image and Gabor palmprint image were fused on the pixel level into a new fused image. Next, a new classifier called KPCA-RBF was designed to extract nonlinear discriminative features by KPCA, and classify objects with RBF. Based on AR database, FERET database, and palmprint database, the single sample discriminant analysis method was realized based on Gabor transform and KPCA-RBF classifier. Experimental results show that multimodal recognition methods clearly outshine single-modal recognition methods, and the GABOR-KPRC with pixel-level fusion achieves better recognition effect than other fusion methods. It was also demonstrated that Gabor transform and KPRC classifier can effectively improve the fusion effect, whether for pixel-level fusion or decision-level fusion.

Economic-Financial Evaluation of Brazilian Companies With Open Capital in the Period 2011 to 2018

The present research aimed to evaluate the economic and financial situation of Brazilian open capital companies between 2011 and 2018. Therefore, an artificial neural network (ANN) backpropagation algorithm was estimated, as well as a discriminant function, using a sample of 285 Brazilian companies with open capitals. As main results, the ANN algorithm was identified as the best method of this evaluation, which relates the company's situation with its most recent past, which proved to be more efficient in companies classification with profitable or loss situation, presenting 83,8% of assertiveness. Moreover, it was possible to identify that the discriminant analysis method did not present statistical significance in the evaluation of these companies. Finally, the important variables in the classification were general liquidity, net margin, debt composition, return on investment, turnover of the asset, physical production index.

Use of discriminant analysis method to identify sex by morphological traits in adult rabbits in Nigeria

Sex assessment plays an important role in rabbit production, but it can be very difficult to determine, especially in the young ones. In this study, canonical discriminant analysis was used to determine which of the morphological traits are the most effective in sex determination in rabbits. Data were taken on 160 rabbits and used for this study on body weight (BWG), body length (BDL), ear length (EAL), heart girth (HTG), and abdominal circumference (ABC). The results from the univariate analysis show manifestation of sexual dimorphism with higher values observed in females for all the morphometric measurements. The canonical discriminant analysis revealed that ABC was the most significant morphological trait as a discriminating variable between the sexes in rabbits. The discriminant function, D = – 8.673 + 1.865 BWG + 0.013 BDL + 0.291 EAL – 0.318 HTG + 0.463 ABC, obtained correctly classified 72.5% of individuals of rabbits. In conclusion, the abdominal circumference of the rabbits in a population could be an important tool for the conservation and improvement of the rabbits’ population.

DISCRIMINANT ANALYSIS TOWARD DEMOGRAPHIC CHARACTERISTICS OF CIKAOBANDUNG VILLAGE COMMUNITY IN CITARUM HARUM PROGRAM

The Indonesian Government through the Citarum Harum program formulates steps to control damage and pollution with various indicators of success, including placing the community around the river to behave in an environmentally friendly manner. The results of research on people's behavior intentions in the Citarum Harum program are influenced by various factors, but the demographic characteristics have not been studied whether each category of gender, age, latest education, and monthly income has clear differences in answering the questionnaire statement indicators and which indicators are make a difference. This research was conducted in RW 02, Cikaobandung Village with a discriminant analysis method. The results showed that there were no clear differences in the gender groups and there were clear differences between the group's latest educational characteristics, monthly income and age. Indicators that differ in age groups are IM2, last education is SN1, and monthly income is IM2, PN2 and BI1.

Analisis diskriminan faktor kecemasan karyawan menghadapi dampak Pandemi Covid-19: Kasus perusahaan manufacturing dan jasa survey

At the beginning of 2020 the world was shocked by the corona virus pandemic (Covid-19) which infected almost all countries in the world. In Indonesia this has an impact on the manufacturing industry sector and survey services. Through this phenomenon, researchers want to look at human psychological factors, how anxious they are about the impact of covid-19, which can lead to potential infection, reduced personal income, companies going bankrupt, massive layoffs, reduced need for staples, and communication between employees which is obstructed. The study design used a cross sectional approach by distributing questionnaires to 220 employees, from the manager, supervisor and staff level using the Discriminant analysis method so that the discriminant function to determine the level of anxiety evaluation was D = -0.003 + 0.634x1 + 0.696x3 - 0.520x4 + 0.168 x5 - 0.864x7.

Research on Consumer Behavior of Wine in HoChiMinh City

This study was conducted to find out the factors affecting the consumers’ choice of wine in HoChiMinh City, Vietnam. The multiple regression model was not statistically significant for finding the relationship between the factors and the Money spent on wine, so discriminant analysis method was used to evaluate the contribution of factors to the differentiation between consumers’ group presented by average bottle consumed per month. The Symbolic benefit factor turned out to be the strongest, followed by Enjoyment benefit factor and Utilitarian & Experiental benefit factor. The findings were used to provide suggestions for wine marketers in Ho Chi Minh City market.