Fisher Discriminant Analysis Research Articles

Patient-rated scales improve the classification accuracy for patients with depression and anxiety disorder: a linear discriminant analysis.

The current study aimed to investigate the performances of clinical scales rated by clinicians and patients as well as cognitive function tests in distinguishing patients with affective and anxiety disorders from healthy controls (HCs). We recruited a total of 122 subjects, comprising 24 patients with bipolar disorder (BD), 34 patients with major depressive disorder (MDD), 29 patients with anxiety disorder (AD), and 35 matched HCs. Three clinician-rated scales and five patient-rated scales were used to quantify clinical symptoms, while four cognitive tests were employed to measure cognitive functions in all subjects. Fisher's discriminant analysis (FDA) was employed to distinguish patients from HCs, as well as to discriminate patient sub-groups from each other. In the FDA model, the prior probability of each group was set as 0.5 in the two-group classification and 0.25 in the four-group classification. The results showed that patient-rated scales achieved higher classification accuracies than clinician-rated scales in identifying MDD and AD from HCs. In contrast, cognitive tests exhibited the lowest accuracy. These findings suggest that patient-rated scales might improve the classification accuracy for patients with MDD and AD.

Utilizing Saliva Metabolomics for Diagnosing Gastric Cancer and Exploring the Changes in Saliva Metabolites After Surgery.

Gastric cancer (GC) is a disease with high prevalence and mortality, but we lack convenient and accurate methods to screen for this disease. Thus, we aimed to search for some salivary biomarkers and explore changes in metabolites in patients' saliva after radical gastrectomy. A total of 152 subjects were divided into three groups (healthy group, GC group, and one-week postoperative group). After simple processing, saliva samples were analyzed by liquid chromatography-mass spectrometry. First, we used total ion chromatography and principal component analysis to determine the metabolite profiles. Next, t-test, partial least squares discriminant analysis, support vector machine, and receiver operating characteristics curve analysis were performed to identify biomarkers. Then, Fisher discriminant analysis and hierarchical clustering analysis were performed to determine the discriminating ability of biomarkers. Finally, we established a generalized linear model to predict GC based on biomarkers, and used bootstrapping for internal validation. Between the healthy and GC groups, we identified four biomarkers: lactic acid, kynurenic acid, 3-hydroxystachydrine, and S-(1,2,2-trichlorovinyl)-L-cysteine. We used stepwise regression to select five metabolites and develop a model with areas under the curve equal to 0.973 in the training dataset and 0.924 in the validation dataset. Between the GC and one-week postoperative groups, we found two differential metabolites: 19-hydroxyprostaglandin E2 and DG (14:0/0:0/18:2n6). Differential metabolites were observed among the three groups. GC could be initially diagnosed on the basis of detection of these biomarkers. Moreover, changes in salivary metabolites in postoperative patients could provide important insights for basic studies.

Fisher discriminant analysis of multimodal ultrasound in diagnosis of cervical metastatic lymph nodes in papillary thyroid cancer.

The purpose of this study was to develop a diagnostic model utilizing multimodal ultrasound parameters to aid in the detection of cervical lymph node metastasis in papillary thyroid cancer (PTC) patients. The study included 84 suspicious lymph nodes from 69 PTC patients, all of whom underwent fine needle aspiration with pathological results. Data from conventional grayscale ultrasound, shear wave elastography (SWE), and superb microvascular imaging were analyzed. Key ultrasound features were compared between benign and metastatic groups to create a diagnostic model using Fisher's stepwise discriminant analysis. The model's effectiveness was assessed with self-testing, cross-validation, and receiver operating characteristic curve analysis. Four features, namely lymphatic hilum (X1), cortical hyperechogenicity (X2), vascular pattern (X4), and SWEmean (X7), were integral to the discriminant analysis, resulting in the equation: Y1 = -3.461 + 2.423X1 + 0.321X2 + 1.620X4 + 0.109X7, Y2 = -8.053 + 0.414X1 + 2.600X2 + 2.504X4 + 0.192X7. If Y1 < Y2, the LN would be diagnosed as metastatic lymph nodes. The model demonstrated an area under the curve of 0.833, with a sensitivity of 83.33% and specificity of 83.33%. The multimodal ultrasound diagnostic model, established through Fisher's stepwise discriminant analysis, proved effective in identifying metastatic lymph nodes in PTC patients.

Prediction of 3D printability and rheological properties of different pineapple gel formulations based on LF-NMR

In this study, a pineapple-starch-xanthan gum system was prepared using fresh pineapple juice, maize starch, and xanthan gum (XG). The feasibility of using low-field nuclear magnetic resonance (LF-NMR) to predict pineapple gels' rheological properties and printability was evaluated. Results indicated that as maize starch and XG increased, the gel transformed from unable to support printed models to a stable shape, eventually becoming too viscous for printing. Principal component analysis and Fisher discriminant analysis classified the gels into four categories based on their rheological properties, aligning with the actual printing results. Pearson correlation analysis showed a strong correlation between the LF-NMR parameters and the rheological properties of gels. The partial least squares (PLS) and back-propagation artificial neural network (BP-ANN) models constructed using the LF-NMR parameters can effectively predict the rheological properties of pineapple gels. Therefore, LF-NMR is a valuable, non-destructive method for quickly assessing pineapple gels' 3D printing suitability.

Information enhanced slow feature analysis integrated with prior fault data for sensitive monitoring of chemical processes

As an effective feature extraction method, slow feature analysis (SFA) has been successfully applied in the domain of chemical process monitoring. However, as an unsupervised method, the basic SFA ignores the key information carried by prior fault data so that many complicated faults cannot be sensitively detected. To address this issue, an enhanced SFA method, termed Information Enhanced SFA (IE-SFA), is proposed by integrating available fault discriminant information to achieve more sensitive detection of complicated chemical process faults. The proposed method builds a primary-auxiliary SFA modeling framework. On the one hand, the normal training data are analyzed to establish the primary SFA model. On the other, prior fault data are integrated to develop an auxiliary monitoring model for providing extra fault-sensitive information. In the auxiliary model, a sample-variable weighted Fisher discriminant analysis method is performed on normal data, fault data, and their respective slow feature components, thereby extracting fault-sensitive features for enhancing the fault detection capability. For full-view fault monitoring, the Bayesian fusion strategy is used to fuse the outcomes from both primary and auxiliary models. The applications on a benchmark Tennessee Eastman chemical process and a three-phase flow process demonstrate that the proposed IE-SFA method provides superior fault detection performance compared to the basic SFA method.

Aquifer Leakage Recharge Controls on CBM Production: A Case Study in the Sanjiao Block, Eastern Ordos Basin, China.

Aquifer leakage recharge poses a prevalent challenge in coalbed methane (CBM) development, severely impeding its efficient production. This study focuses on the Sanjiao Block, located on the eastern margin of the Ordos Basin, and provides a comprehensive evaluation of the impact of aquifer leakage recharge on CBM well productivity, employing hydrochemical characteristics and numerical simulation. Fisher's discriminant analysis reveals a close association between external water sources for CBM wells in the Taiyuan Formation and the hydrodynamic environment: in the western stagnant zone, hydrochemical characteristics resemble those from the Shanxi Formation; in the eastern strong runoff zone, water from the Taiyuan Formation directly contributes to CBM well development; in the central weak runoff zone, hydrochemical characteristics suggest mixed water sources from the Shanxi Formation and Taiyuan Formation. The numerical simulation employs orthogonal experiments to quantify the sensitivity of aquifer geological parameters to CBM production, ranked from strong to weak for aquifer types, leakage channel properties, and aquifer physical properties. The fundamental reason for disparities in the efficacy of leakage recharge lies in categorizing aquifers into finite and infinite recharges based on their water supply capacity. The properties of leakage channels, including the location and scale, manifest as effects on the magnitude and shape of gas production characteristics in infinite and finite recharge aquifers, respectively. Furthermore, a discriminant flowchart of CBM production is presented, delineating the production characteristics of CBM wells under the influence of aquifer leakage recharge into six patterns and illustrating their distribution in the study area. This discriminant process provides scientific guidance for analyzing CBM production characteristics and evaluating potential under the influence of aquifer leakage recharge.

Lung and colon classification using improved local Fisher discriminant analysis with ANFIS

Lung and colon classification using improved local Fisher discriminant analysis with ANFIS

Fault diagnosis of rolling bearing based on hierarchical discrete entropy and semi-supervised local Fisher discriminant analysis

This paper addresses challenges in extracting effective information from rolling bearing fault signals and handling strong correlations and information redundancy in high-dimensional feature samples post-extraction. A rolling bearing fault diagnosis method is proposed on the basis of hierarchical discrete entropy (HDE) combined with semi-supervised local Fisher discriminant analysis (SELF). Firstly, hierarchical discrete entropy is extracted from signals preprocessed via variational mode decomposition. We assess entropy stability under different parameters using the coefficient of variation and select optimal parameters accordingly. Secondly, we employ the SELF method to remap the multidimensional feature sample set extracted, performing dimensionality reduction. Finally, a fault diagnosis model classifies the dimensionality-reduced feature samples for fault identification. Experimental results demonstrate that entropy samples extracted via HDE achieve higher diagnostic accuracy after dimensionality reduction with the SELF method. Specifically, accuracy rates of 100 % and 98.2 % are achieved for two types of fault samples, respectively, validating the feasibility and effectiveness of our approach.

A novel method for detecting cardiac arrhythmias in electrocardiogram signals using the ANFIS classifier

In general, ventricular repolarization instability with Premature Activations (PA) plays a significant role in the detection of arrhythmia using an electrocardiogram (ECG) signal. However, clinical detection of this instability is challenging. In this work, a unique technique for analyzing QT Interval (QTI) dynamics unreliability and other abnormalities in the ECG signal are utilized to detect ventricular tachycardia based on the identified anomalies. Further, a feature extraction method based on Chopped Displacement Gaussian (CDGa) is adopted and the features are retrieved from the CDGa signal and its size is reduced using Fisher Discrimination Analysis (FDA). Also, the results of the FDA are fed into the Adaptive Neuro-Fuzzy interference (ANFIS) classifier. The performance of the ANFIS classifier is enhanced in this study by integrating the Grasshopper optimization algorithm for optimizing network parameters. As a result, the values in the signals are predicted using an adaptive Least Mean Square (LMS)-based prediction algorithm, which is utilized to forecast the future status of VT-affected patients. Results indicate that the proposed work has an overall accuracy of 96 % which is higher than any other conventional methods. Also, the various additional performance criteria are tested, and it is demonstrated that the CDGa with adaptive LMS outperforms all previous approaches.

Which dimensions of nature contact in Urban Green Spaces most significantly contribute to mental wellbeing? A multidimensional analysis in Brazilian metropolitan cities

BackgroundUrban environments pose challenges to mental health, an issue that Urban Green Spaces (UGS) can potentially mitigate. While the benefits of nature contact for mental wellbeing are recognized, a multidimensional analysis remains unexplored. PurposeThis study aims to fill this gap by examining the association between nature contact within UGS and mental health. It underscores the importance of considering multiple dimensions of nature engagement—such as naturalness, intensity, duration, frequency, and infrastructure—in enhancing psychological wellbeing. MethodA comprehensive analysis, including canonical correlation, multivariate analyses of variance, and Fisher discriminant analysis, was applied to survey data from several Brazilian metropolitan cities to assess how different aspects of nature contact influence mental health. Results and conclusionsFindings reveal association between these dimensions and mental wellbeing indicators, highlighting the importance of a multidimensional perspective. Practical implicationsResults advocate for incorporating diverse aspects of nature contact in UGS design and policy-making to enhance urban dwellers' mental health. Future directionsFurther research should focus on longitudinal studies and explore the mediating effects of socio-demographic factors. Additionally, expanding research to include other developing countries will provide valuable comparative insights.

The Causes of Platelet Aggregation in Version 6.4 Trima Accel Automated Blood Collection System and the Comparison of Two Intervention Measures

To explore the causes of platelet aggregation in version 6.4 Trima Accel automated blood collection system and the effect of 2 intervention measures. The data on platelet aggregation (n=61) and non-aggregation (n=323) of 61 donors in 2020 were collected and the causes of aggregation were analyzed. Then the 72 donors with platelet aggregation in 2021 were randomized into intervention group A (increasing the anticoagulant-to-blood ratio) and intervention group B (wrapping the donor's arm with an electric blanket to keep warm and improve the blood flow speed). The collection time, average blood flow speed, number of machine alarms, anticoagulant usage, deaggregation and citrate reaction of the two groups were compared. Platelet aggregation was negatively correlated with the average blood flow speed (r =-0.394) and positively correlated with the collection time (r =0.458). The equations for predicting aggregation and non-aggregation were constructed based on Bayesian and Fisher discriminant analysis, and the predicted accuracy was 77.1%. The comparison of the effects of two intervention measures showed that the average blood flow speed in group B was higher than that in group A; the collection time, number of machine alarms, anticoagulant usage and proportion of citrate reaction in blood donors in group B were all lower than those in Group A, all these differences were significant (P < 0.05). In the entire cohort in 2021, 90.28% of the products were immediately deaggregated after collection, and 9.72% of the products were deaggregated within 4 hours. There was no statistically significant difference in deaggregation between the two intervention groups (P >0.05). During apheresis platelet collection, the predictive equations for aggregation and non-aggregation can be used to predict the occurrence probability of aggregation, and the intervention can be made in advance. Both intervention measures are effective in reducing platelet aggregation, however, measure B has the advantages of improving the speed of blood collection, shortening the collection time, reducing the alarm frequency and the anticoagulant usage, and reducing the incidence of citrate reaction in blood donors.

Classification of major species in the sericite-Artemisia desert grassland using hyperspectral images and spectral feature identification.

The species composition of and changes in grassland communities are important indices for inferring the number, quality and community succession of grasslands, and accurate monitoring is the foundation for evaluating, protecting, and utilizing grassland resources. Remote sensing technology provides a reliable and powerful approach for measuring regional terrain information, and the identification of grassland species by remote sensing will improve the quality and effectiveness of grassland monitoring. Ground hyperspectral images of a sericite-Artemisia desert grassland in different seasons were obtained with a Soc710 VP imaging spectrometer. First-order differential processing was used to calculate the characteristic parameters. Analysis of variance was used to extract the main species, namely, Seriphidium transiliense (Poljak), Ceratocarpus arenarius L., Petrosimonia sibirica (Pall), bare land and the spectral characteristic parameters and vegetation indices in different seasons. On this basis, Fisher discriminant analysis was used to divide the samples into a training set and a test set at a ratio of 7:3. The spectral characteristic parameters and vegetation indices were used to identify the three main plants and bare land. The selection of parameters with significant differences (P < 0.05) between the recognition objects effectively distinguished different land features, and the identification parameters also differed due to differences in growth period and species. The overall accuracy of the recognition model established by the vegetation index decreased in the following order: June (98.87%) > September (91.53%) > April (90.37%). The overall accuracy of the recognition model established by the feature parameters decreased in the following order: September (89.77%) > June (88.48%) > April (85.98%). The recognition models based on vegetation indices in different months are superior to those based on feature parameters, with overall accuracies ranging from 1.76% to 9.40% higher. Based on hyperspectral image data, the use of vegetation indices as identification parameters can enable the identification of the main plants in sericite-Artemisia desert grassland, providing a basis for further quantitative classification of the species in community images.

Vortex rope identification in Francis turbine based on cyclostationary extended dictionary learning

Francis turbine is one of the most commonly used hydraulic machinery for hydroelectric power generation, but its stability is frequently jeopardized by vortex rope. It is crucial to promptly and accurately detect vortex rope for the reliable operation of turbine unit. To address this challenge, the Cyclostationary Extended Dictionary Learning (CEDL) approach is proposed to identify vortex rope in Francis turbine. CEDL utilizes the Fisher discrimination criterion and low-rank constraints through the preprocessing and extending strategies to achieve accurate identification. Preprocessing specifically refers to the construction of filter for raw data based on cyclostationarity Then, the trained dictionary is used to extract features, and a linear classifier is developed based on these features. To evaluate the proposed method, vortex rope experiments are conducted in a Francis turbine under five conditions, and every condition includes four states: normal state, initial vortex rope, stable vortex rope and severe vortex rope. The results reveal three main findings. Firstly, the trained atoms in each sub-dictionary exhibit unique characteristics such as tonal frequency at 7 kHz and broadband frequency during 12–20 kHz, which are linked to the evolution stages of vortex rope. Secondly, the dictionary trained for a specific condition can achieve a classification accuracy of up to 90%, and even exceed 97% in some cases. Finally, the dictionary trained in a specific working condition can achieve relatively high classification accuracy in the scenarios of other working conditions.

Riemannian Geodesic Discriminant Analysis–Minimum Riemannian Mean Distance: A Robust and Effective Method Leveraging a Symmetric Positive Definite Manifold and Discriminant Algorithm for Image Set Classification

This study introduces a novel method for classifying sets of images, called Riemannian geodesic discriminant analysis–minimum Riemannian mean distance (RGDA-MRMD). This method first converts image data into symmetric positive definite (SPD) matrices, which capture important features related to the variability within the data. These SPD matrices are then mapped onto simpler, flat spaces (tangent spaces) using a mathematical tool called the logarithm operator, which helps to reduce their complexity and dimensionality. Subsequently, regularized local Fisher discriminant analysis (RLFDA) is employed to refine these simplified data points on the tangent plane, focusing on local data structures to optimize the distances between the points and prevent overfitting. The optimized points are then transformed back into a complex, curved space (SPD manifold) using the exponential operator to enhance robustness. Finally, classification is performed using the minimum Riemannian mean distance (MRMD) algorithm, which assigns each data point to the class with the closest mean in the Riemannian space. Through experiments on the ETH-80 (Eidgenössische Technische Hochschule Zürich-80 object category), AFEW (acted facial expressions in the wild), and FPHA (first-person hand action) datasets, the proposed method demonstrates superior performance, with accuracy scores of 97.50%, 37.27%, and 88.47%, respectively. It outperforms all the comparison methods, effectively preserving the unique topological structure of the SPD matrices and significantly boosting image set classification accuracy.

Fisher discrimination multiple kernel dictionary learning for robust identification of nonlinear features in machinery health monitoring

In sparse representation-based classification, Fisher discrimination dictionary learning (FDDL) has attracted widespread attention due to its advantages such as fewer parameters and good dictionary discriminability. However, due to its linear nature, it is difficult to handle nonlinear features. Kernel-based nonlinear transformation enables dictionary learning to capture nonlinear features embedded in samples, but traditional single-kernel methods have limited performance. In this paper, a Fisher discrimination multiple kernel dictionary learning (FDMKDL) method is proposed, in which Fisher discriminative criterion is imposed on both high-dimensional samples and coding coefficients. Specifically, we derive the kernel version of FDDL, i.e., Fisher discrimination kernel dictionary learning (FDKDL) to learn nonlinear features and promote dictionary discriminability. Meanwhile, to avoid the problem of poor adaptability and possible manual selection caused by single-kernel methods, we further derive a flexible multiple kernel learning (MKL) framework, which utilizes the complementary information of multiple kernel functions to adaptively obtain the optimal weights and synthesize a discriminative kernel space. Finally, FDMKDL combines FDKDL with this MKL framework to obtain a more discriminative dictionary. Experimental evaluations conducted on two datasets demonstrate the effectiveness and robustness of the proposed FDMKDL method in learning nonlinear features for machinery health monitoring when compared to several state-of-the-art methods.

Fault diagnosis for blast furnace ironmaking process based on randomized local fisher discriminant analysis

AbstractFault diagnosis plays a vital role in ensuring the operation safety of blast furnaces and improving the quality of molten iron in the ironmaking and steelmaking industry. The blast furnace ironmaking process (BFIP) is intrinsically nonlinear. To address the nonlinearity issue of BFIP, a novel fault diagnosis approach that combines the randomized method, local structure information, and Fisher discriminant analysis is proposed in this paper. Using a randomized feature map, the process data is first mapped onto a randomized explicit low‐dimensional feature space. Compared to kernel methods, explicit low‐dimensional random Fourier features considerably reduce the computational cost, particularly for real‐time fault diagnosis for a large training dataset or a large‐scale process. Additionally, the local structure information contained in the randomized low‐dimensional feature space is extracted. The fault diagnosis performance is improved through the exploration of the local structure of random Fourier features. Finally, the blast furnace iron‐marking process state is determined using Bayesian inference. Case studies on a real‐world BFIP are carried out to demonstrate the superior performance of the proposed method in comparison with other related methods.

Semi-supervised Kernel Fisher discriminant analysis based on exponential-adjusted geometric distance

Semi-supervised Kernel Fisher discriminant analysis based on exponential-adjusted geometric distance

Multi-Scale Dense Graph Attention Network for Hyperspectral Classification

In recent years, numerous deep learning-based methods have gained increasing attention in hyperspectral classification, particularly the Graph Neural Network, which exhibits superior capabilities in structural description. However, a single graph structure is not suitable for hyperspectral feature representation. Therefore, we propose a novel Multiple-Scale graph network structure, known as the Multi-Scale Dense Graph Attention network for hyperspectral classification. Firstly, semi-supervised local Fisher discriminant analysis and superpixel segmentation were employed for dimensionality reduction and multi-scale graph construction, respectively. Secondly, Spectral-Spatial convolution is applied to extract shallow features from the image. Subsequently, an improved graph self-attention network is sequentially applied to each scale graph, and the different scale graphs are densely connected through spatial feature alignment modules, designed using twice matrix multiplication. Finally, the combined pixel-level feature map from multiple graph spaces is derived, and Spectral-Spatial convolution is employed to fuse the abundant feature maps for hyperspectral classification. Experimental results on various hyperspectral datasets demonstrate the superiority of our MSDesGATnet over many state-of-the-art methods. The code is available at https://github.com/l7170/MSDesGAT.git.

Construction of "De-Capacity Reduction" financial performance index for Chinese coal industry enterprises ——based on Fisher discriminant analysis

In February 2016, the Chinese government focused on removing excess capacity in coal industry enterprises, and the research goal of the paper was to determine how much impact this will have on the financial performance of coal industry enterprises. The paper collected the financial performance indicators of Chinese state-owned coal industry enterprises from 2011 to 2021, and discriminant analysis was used to calculate the financial performance index evaluation system. The conclusions are: (1) From 2011 to 2016, the financial performance index of Chinese state-owned coal industry enterprises before De-Capacity continued to decline, from 2.062 in 2011 to 1.639 in 2016; In 2017–2021, the financial performance index of Chinese state-owned coal industry enterprises after De-Capacity continued to rise, from 1.482 in 2017 to 1.515 in 2021. (2) From 2011 to 2020, the cumulative financial performance index for the whole trade of state-owned coal industry in the past decade was 18.340, with state-owned large coal industry enterprises having the best financial performance, with a 10-year cumulative index of 20.618, followed by state-owned medium-sized coal industry enterprises, with a 10-year cumulative index of 17.944, and the worst among state-owned small coal industry enterprises, with a 10-year cumulative index of 17.271. (3) If the market adjustment started in 2012 is also considered as a component of "De-Capacity", two pressures from the market and the government have prompted the transformation of state-owned coal industry enterprises. The industry wide financial performance index has increased from 1.554 in 2012 to 1.559 in 2020, with an average annual increase of 0.04 %.

Chemical composition and discrimination with volatile profiles of Yongchuan Xiuya green tea with different baking treatments

AbstractThis study aimed to explore the effects of different baking treatments on the quality of Yongchuan Xiuya (YCXY) green tea. It was found that a long time baking at low temperature was beneficial to keep green colour, faint scent, mellow and fresh taste quality, whereas baking under high temperature was adverse to the quality. Baking treatments slightly regulated (−)‐epigallocatechin, (−)‐epicatechin, (−)‐gallocatechin gallate, total chlorophyll and carotenoid. As the baking temperature rose, the content of tea polyphenols, gallic acid, catechins, caffeine, soluble sugar and polyphenols/amino acids ratio obviously decreased. A total of 40 kinds of volatiles were detected in these six tea samples. A model for aroma type discrimination was successfully established based on partial least squares‐discriminant analysis (PLS‐DA). Ten kinds of volatile substances were the key characteristic markers for the faint scent, chestnut aroma and high‐fired aroma types of YCXY green tea. 1‐hexanol, hotrienol and dimethyl sulfide were furtherly used to discriminant aroma type based on Fisher discriminant analysis (FDA).