Fisher Discriminant Method Research Articles

Research on Face Recognition Algorithm Based on Image Processing.

While network technology is convenient for our daily life, the problems that are exposed are also endless. The most important thing for everyone is information security. In order to improve the security level of network information and identify and detect faces, the method used in this paper has improved compared with the traditional AdaBoost method and skin color method. AdaBoost detection is performed on the image, which reduces the probability of false detection. The experiment compares the experimental results of the AdaBoost method, the skin color method and the skin color + AdaBoost method. All operations in the KPCA and KFDA algorithms are performed by the inner product kernel function defined in the original space, and no specific non-linear mapping function is involved.The full name of KPCA is kernel principal component analysis. The full name of KFDA is kernel Fisher discriminant analysis. Combining the zero-space method kernel discriminant analysis method improves the ability of discriminant analysis to extract non-linear features. Through the secondary extraction of PCA features, a better recognition result than the PCA method is obtained. This paper also proposes a zero-space based Fisher discriminant analysis method. Experiments show that the zero-space-based method makes full use of the useful discriminant information in the zero space of the intraclass dispersion matrix, which improves the accuracy of face recognition to some extent.If you choose the polynomial kernel function, when d = 0.8, KPCA has a higher recognition ability. When d = 2, the recognition rate of KFDA and zero space-based KFDA is the largest. For polynomial functions, in general, d = 2.

Fisher discriminant analysis method applied in drought detection: an instance in an alpine meadow ecosystem

Abstract Fisher discriminant analysis can comprehensively take multiple factors into consideration and effectively conduct separations between two classes. If it can be used to detect the occurrences of drought, drought can be detected more effectively and accurately. Based on 9-year carbon flux and corresponding meteorological data, soil water content (SWC) and vapor pressure deficit (VPD) were selected as the discriminant factors. Drought occurrences were detected by applying the Fisher discriminant analysis method in an alpine ecosystem in Tibet. Fisher discriminant analysis was successfully applied to detect drought occurrence in an alpine meadow ecosystem. The soil water deficit and atmospheric water deficit were comprehensively taken into consideration. Consequently, this method could detect the onset and end date of droughts more accurately and reasonably. Based on the characteristics of drought and non-drought samples, the discriminant equation was constructed as y = 24.46SWC − 4.60VPD. When y > 1, the days were distributed above the critical line. In addition, when y was greater than one for more than 10 days, it was labeled as one drought event. If the interval between two drought processes was less than 2 days, it was considered one drought event. With increasing the study period and continued accumulation of observation data, the discriminant equation could be further optimized in the future, resulting in more accurate drought detection.

Research on Financial Risk Early Warning in the Online Game Industry Based on Random Forest and Fisher Discriminant Method

With the rapid rise of the online game industry and the intensification of market competition, online game enterprises face different degrees of financial risks. It is necessary to establish an effective financial risk early warning model. Based on the online game industry, this paper constructs an index system from six dimensions, and makes an empirical study on financial risk early warning. First of all, a financial risk early warning model based on the random forest is constructed, and the prediction accuracy is as high as 100%, but the machine learning model has poor explanatory ability. Therefore, according to the index of random forest screening, a financial risk warning model based on the Fisher discriminant method is established. This model optimized the prediction effect of the original fisher's discriminant model and the prediction accuracy reached 87.5%. Finally, suggestions are made from the three aspects of cash flow, solvency and profitability of online game enterprises, and national support policies.

Classification and evaluation of tight sandstone reservoirs based on diagenetic facies: a case study on Chang 6 reservoir in the center-west Ordos Basin

AbstractTight sandstone reservoirs dominated by are developed in the Chang 6 oil layer group of the Yanchang Formation in the central-western part of the Ordos Basin. Featuring the lacustrine delta facies, Chang 6 formation in the center-west area of Ordos Basin shows an increasing petroleum reserve expectation. Its exploitation practice, however, has many problems caused by tight sandstone reservoir features. According to diagenetic and pore analysis, the diagenetic facies in the study area are grouped into four types: chlorite-film-intergranular-pore, feldspar-dissolution, clay-cemented-micropore, carbonate-cemented-tightness for their obvious differences in mineral feature and pore evolution. By introducing the comprehensive classification parameter synthesized from 9 other parameters, the reservoir quality is divided up into four levels: I(Feci > 1), II(3 ≤ Feci ≤ 7), III(-2 ≤ Feci ≤ 3), IV(Feci ≤ -2). The reservoir quality division matches well with the diagenetic facies group. To decide the diagenetic type and reservoir quality division in all wells, the logging data are utilized with the Fisher discriminant method, which has obtained a good performance. The method enables the reservoir quality analysis expanding to all wells from samples, which is helpful for exploitation of the study area.

A non-destructive detection method for evaluating beef taste quality based on electrochemical PVC membrane sensor

A polyvinyl chloride (PVC) membrane sensor was developed to accurately detect beef taste quality grades. The beef taste was identified by the Fisher discriminant and verified by sensory evaluation. The PVC membrane sensor with the maximum open circuit potential (OCP) value and excellent performance was composed of 0.4 mL of dibutyl phthalate (DBP), 0.25 mL of lauryl ether phosphate, 3.6 mg of magnesium stearate and 6 mg of thermoplastic polyurethanes (TPU). Texture analyzer tests showed that the membranes showed desired physical properties, and the elasticity, viscosity and cohesion of the PVC membrane sensor were 4.74 mm, 2.17 mJ and 1.89 respectively. Scanning electron microscopy (SEM) showed the electrode immersed for 6 h without separation with PVC membrane. The coefficient of variation was less than 10% with a storage period of 7 months. Sensory evaluation showed that the beef sensory rated grades array determination by the Fisher discriminant method to verify the sensitivity of ammonia-sensitive substance-modified PVC membrane sensor had an accuracy of 93.3%.

Rough Set-Fisher Discriminant Analysis Method for Prediction of Classification of Rock Burst Risk

This paper introduces the rough set theory, combined with the Fisher discriminant method to more accurately predict the risk level of rock burst. Firstly, based on the example of Yanshitai coal mine in Chongqing, we determine the influencing factors of rock burst risk; then, the evaluation indicators are reduced by rough set theory to obtain the key attributes; finally, the reduced key attributes are used as the discriminant factors of the rough set-Fisher discriminant model to test. According to the research results, the rough set-Fisher discriminant analysis method eliminates redundant indicators and reduces the number of indicators after reducing the evaluation indicators, achieving efficient prediction of the risk level of rock burst.

Onboard target detection in hyperspectral image based on deep learning with FPGA implementation

Onboard target detection of Hyperspectral Imagery (HSI) is widely adopted in the field of remote sensing. It requires high detection accuracy and low computational complexity for processing a large volume of HSI data. In this study, a Locally Preserving Discriminative Broad Learning (LPDBL) was introduced for target detection due to its simple, excellent generalization ability, and its competitive performance. The detection was done through spatial-spectral information, band selection, and estimation of the covariance matrix. The fisher discriminant method was used to reduce the dimension of HSI data. Weights was adjusted through manifold regularization in order to enhance the detection ability of the proposed method. To study the performance of the proposed LPDBL, experiment was conducted on two different datasets of HSI. The results revealed that the proposed method performed better and suitable for target detection. The LPDBL was implemented on Virtex-7 Field Programmable Gate Array (FPGA) board. Furthermore, the LPDBL technique was practically validated by two different techniques such as a broad learning system (BLS) and Automatic Target Detection in HSI (ATD-HSI). The result obtained from the FPGA was very close to the actual target position.

Fast Fisher Discrimination of Water-Rich Burnt Rock Based on DC Electrical Sounding Data

Direct current (DC) electrical sounding was performed to quickly identify the location of potentially dangerous water hidden in burnt rock (formed by spontaneous combustion of the coal). The Fisher discriminant method was used to generate the functional relationship between borehole water inflow and DC electrical sounding data, and a model was established to identify the water-enriched burnt rock areas. Based on a reevaluation of the training samples, the accuracy of the water-rich discrimination model was found to be 89.1%. Finally, the water enrichment in the burnt area was predicted based on DC sounding data from 576 survey points in five exploration lines, and the predictions were compared with the subsequent water inflow data from boreholes. We found that the predicted results were highly consistent with the water inflow data in the boreholes. Thus, the feasibility of using this approach was verified.

Magnetic resonance image biomarkers improve differentiation of benign and malignant parotid tumors through diagnostic model analysis.

To explore the effectiveness of magnetic resonance image (MRI)-based biomarkers for identifying benign and malignant parotid tumors via diagnostic model analysis. This retrospective study included 109 patients (development cohort and validation cohort) who underwent MRI preoperatively, including T1- and T2-weighted images. Parameters based on 2D or 3D texture analysis were extracted from tumor lesions by MaZda software, fisher discriminant and bootstrap method were used to perform parameter reduction, diagnostic models with the selected biomarkers were established along with clinical data, model performance (discrimination and calibration) was furtherly evaluated by internal and external validation, decision curve analysis was applied to measure the improvement of clinical benefits. S(5,5) Entrop, S(0,1) ASM, WavEnHH (s-4), S(1,1,0) Entropy and Perc.10% were significantly associated with the pathological diagnosis of parotid tumor (benign versus malignancy), when adding these biomarkers to the regression analysis, model performance significantly improved in the development cohort (likelihood-ratio-test; p < 0.05, with an increase of AUC from 0.72 (reference model) to 0.85), and these results were maintained in a small external validation cohort. Decision curve analysis indicated that clinical benefit was greater with the application of MRI-based biomarkers. MRI-based texture analysis is proven to be an effective tool in differentiating benign and malignant parotid tumors, preoperative diagnosis was improved with the selected biomarkers compared to the reference model.

Water Source Discrimination in a Multiaquifer Mine Using a Comprehensive Stepwise Discriminant Method

Previously proposed discriminant methods cannot accurately identify water sources in a complex multiaquifer mine. Based on statistical analysis of the water chemistry of samples collected at the Xinji no. 2 multiaquifer coal mine, a comprehensive stepwise discriminant method was proposed for this purpose. Characteristic ion contrast and ion proportional coefficients were applied to aquifers with distinct chemical characteristics to establish a characteristic index discrimination system. Aquifers with small differences in water chemistry were identified by the Fisher discriminant method. Different methods (first simple ones, followed by more complex ones) were used to distinguish the water sources of different aquifers. This approach enabled us to identify water sources for the Xinji no. 2 mine and should be tried for other sites with similar hydrogeological conditions.

Automatic Classification Algorithm for Diffused Liver Diseases Based on Ultrasound Images

Diffuse liver diseases such as fatty liver and cirrhosis, are leading causes of disability and fatality across the world. Early diagnosis of these diseases is extremely important to save lives and improve the effectiveness of treatment. This study proposes a non-invasive method for diagnosing liver diseases using ultrasound images, by classifying liver tissue as normal, steatosis, or cirrhosis, using feature extraction, feature selection, and classification. First, the correlation, homogeneity, variance, entropy, contrast, energy, long run emphasis, run percentage, and standard deviation are determined. Second, the most efficient features are selected based on the Fisher discriminant and manual selection methods. Third, three voting-based sub-classifiers are used, namely, the normal/steatosis, normal/cirrhosis, and steatosis/cirrhosis classifiers. The final liver tissue classification is based on the majority function. Our classification method provides two key contributions: combination of two different feature selection methods, avoiding the limitations of each method while benefiting from their strengths; and classifier categorization into three sub-classifiers, where the overall classification is based on the decision of each individual sub-classifier. We obtained recognition accuracies for the normal/steatosis, normal/cirrhosis, and steatosis/cirrhosis classifiers as 95%, 95.74%, and 94.23%, respectively, and an overall recognition accuracy of 95%, which outperforms other methods.

Characteristics and quantitative evaluation of volcanic effective reservoirs: A case study from Junggar Basin, China

The Permian Jiamuhe Formation in Jinlong-2 Block is an unconventional volcanic reservoir that has been a major target of oil production in the northwest margin of the Junggar Basin, China. This study focuses on analyses of geological, well-logging and production data to understand the characteristics and to set up quantitative evaluation method on volcanic reservoirs. The geological data reveals that the lithology mainly includes andesitic (welded) breccia, andesitic/basaltic brecciated lava and andesite. The reservoir space is mainly composed of stomata and dissolution pore, followed by intercrystalline pore and intergranular pore, therefore is characterized by low to medium low porosity (ϕ) and ultra-low to low permeability (k). The mercury injection capillary pressure curves have shown that the microscopic pore and throat of effective reservoirs mainly express in fine pore type with unimodal coarse state, partial coarse state and bimodal partial coarse state. Moreover, limits (ϕ ≥ 8%, k ≥ 0.03 × 10-3μm2) of effective volcanic reservoirs have been determined by oil test and cross plot of porosity and resistivity. Thus, based on the analysis of macroscopic and microscopic characteristics, we optimize the K-means clustering analysis method and typical Fisher's discriminant method to set up quantitative classification and evaluation criteria and discriminant functions, which divide the volcanic effective reservoir into 3 classes accordingly. Our results have been applied to the development test area, the average daily oil production of deployed horizontal wells is 204 bbl/d, and the average cumulative oil production for one year is 68 Mbbl. This quantitative classification method may provide strong technical supports for the efficient development of volcanic reservoir.

A Risk Assessment of a Water-Sand Inrush during Coal Mining under a Loose Aquifer Based on a Factor Analysis and the Fisher Model

AbstractThis paper aims to investigate the safety problems related to coal mining under a loose aquifer, and uses the Factor Analysis (FA) and Fisher discriminant methods to analyze and assess the ...

Local Non Zero Eigen Value Preservation Based Expression Recognition

This work proposes an finest mapping from features space to inherited space using kernel locality non zero eigen values protecting Fisher discriminant analysis subspace approach. This approach is designed by cascading analytical and non-inherited face texture features. Both Gabor magnitude feature vector (GMFV) and phase feature vector (GPFV) are independently accessed. Feature fusion is carried out by cascading geometrical distance feature vector (GDFV) with Gabor magnitude and phase vectors. Feature fusion dataset space is converted into short dimensional inherited space by kernel locality protecting Fisher discriminant analysis method and projected space is normalized by suitable normalization technique to prevent dissimilarity between scores. Final scores of projected domains are fused using greatest fusion rule. Expressions are classified using Euclidean distance matching and support vector machine radial basis function kernel classifier. An experimental outcome emphasizes that the proposed approach is efficient for dimension reduction, competent recognition and classification. Performance of proposed approach is deliberated in comparison with connected subspace approaches. The finest average recognition rate achieves 97.61% for JAFFE and 81.48% YALE database respectively.

The Application of the Fisher Discriminant Method in Water Flooded Layer Discriminant

The Application of the Fisher Discriminant Method in Water Flooded Layer Discriminant

Metameric effects on peridot by changing background color.

Peridot's yellowish-green color is not only produced by ${{\rm Fe}^{2+}}$Fe2+ but is also influenced by background, observer, illuminance, and color temperature of the light source. In this research, we studied the most effective background for peridot color grading under a 6504K fluorescent lamp. Ninety-five gem-quality peridot samples from China, Pakistan, and Myanmar were studied using electron probe micro-analyzer, spectrophotometer, Munsell neutral gray backgrounds, and standard gold alloy backgrounds. The results provided the color effects of 24K, 22K, 20K, 18K, and 16K gold alloy backgrounds and Munsell neutral gray backgrounds on the peridot's color. It was found that the Munsell N9 background seems to be the most effective background for peridot color grading. Using the Munsell N9 background, peridot colors were graded into three levels from good to bad: Fancy Intense, Fancy Deep, and Fancy by using K-means clustering analysis and Fisher discriminant analysis methods. The peridot's color level reverse phenomenon should be considered when the background varies between Munsell N7 and N9 gray.

DISCRIMINANT ANALYSIS THROUGH FISHER METHOD ON STUDENT'S MATERIALS BUILDING IN SMP 1 BANDA ACEH

The study is done for determining how many students and how the percentage of students who have mastered the material geometry about prism and pyramid, and getting the discriminant function about the mastery of the material. The study population was the entire eighth grade students of SMP Kasih Banda Aceh while the sample were students of class VIII-1 and VIII-8 to 66 students. Based on the research that has been done using the fisher discriminant analysis method, 18,18% of students have mastered the material geometry and 81,82% of students have not mastered the material geometry. It means that from 66 students only 12 students were able to master the material geometry about well- prism and pyramid. The discriminant function that is formed is and .

Application of cluster analysis and discriminant analysis in quality grading of jadeite red

A more effective grading standard for jadeite-jade red was established through combining gemology with statistics. 120 jadeite-jade (red) samples were tested by X-Rite SP62 integral spherical spectrophotometer under standard light source D65 to quantify the lightness (L*), hue (hab°) and chroma (Cab*) of jadeite-jade red based on CIE 1976 L*a*b* uniform color space theory. K-Means clustering analysis method in SPSS 22.0 statistical analysis software was used to grade the color of red jadeite-jade. Fisher discriminant analysis method was used to verify the feasibility of the classification and to find an objective and effective color grade evaluation method. Finally, the jadeite-jade red was divided into five grades: Fancy Vivid, Fancy Deep, Fancy Intense, Fancy dark and Fancy.

Application of Fisher discriminant method in the facies division of lake facies-Taking the third member of Shahejie Formation in Dongying Sag as an example

ABSTRACTA large number of lacustrine mudstones were formed in the third member of Shahejie Formation in the Paleogene in the DongyingSag. It is the main source rock and lithologic reservoir development layer in Dongying area. Based on the viewpoints of the predecessors, core observation, and logging data analysis, the lithologic characteristics of the third member of Shahejie Formation (including mineral content, sedimentary structure and organic matter content) were summarized. With the logging method, the logging curves such as GR, AC and R25 were selected to establish the recognition mode. Fisher discriminant analysis was performed using SPSS software to establish a quantitative partitioning scheme. The experimental results show that the lacustrine mudstones in the third member of Shahejie Formation in Dongying Sag can be subdivided into seven types of lithofacies, each of which has different identification characteristics; the discriminant equation can be established through discriminant analysis to distinguish different types of facies. It provides a research idea for the identification and prediction of lithofacies for the well sections lacking coring data and logging data.

Combination of mRNA of Repair-related Genes in Rat Skeletal Muscles for Wound Age Estimation.

Objective To investigate the estimation of early and mid-term wound age by a combination of four mRNAs, the DNA polymerase delta-interacting protein 3 （POLDIP3） mRNA, regulator of chromosome condensation 1 like （RCC1L） mRNA, proline-rich 5 （PRR5） mRNA, and ribonucleic acid export 1 （RAE1） mRNA in rats skeletal muscles. Methods The model of rat skeletal muscle contusion was established, and then contusion area muscle tissue was extracted 4, 8, 12, 16, 20, 24, 28, 32, 36, 40, 44 and 48 h after injury. Histomorphological changes during the repair process after rat skeletal muscle contusion were observed. The relative expressions of Poldip3, Rcc1l, Prr5 and Rae1 mRNAs were detected by reverse transcription real-time quantitative polymerase chain reaction （RT-qPCR）. Different stages of wound age were classified by using the expression patterns of four genes at various time points after injury. The accuracy of the results was verified by Fisher discriminant analysis. Results Histomorphological results showed that the repair process after skeletal muscle contusion occurred with the prolonging of time. Through combination of the expression trends of the four kinds of mRNAs, the 48 h after injury could be divided into three periods, 4-12 h, 16-28 h and 32-48 h. The Fisher discrimination method showed that the classification accuracy rates of the three periods were 83.3%, 75.0% and 73.3%, respectively. Conclusion The classification discrimination based on the relative expression of every gene has a higher accuracy, and the accuracy of wound age estimation with combination of mRNA relative expressions is higher than that with a single indicator. By combining with Fisher discrimination method, this method can be used for early and mid-term wound age estimation.