Probabilistic Fisher discriminant analysis based on Gaussian mixture model for estimating shale oil sweet spots

The delineation of shale oil sweet spots is a crucial step in the exploration of shale oil reservoirs.A single attribute such as total organic carbon(TOC)is conventionally used to evaluate the sweet spots of shale oil.This study proposes a probabilistic Fisher discriminant approach for estimating shale oil sweet spots,in which the probabilistic method and Gaussian mixture model are incorporated.Statistical features of shale oil facies are obtained based on the well log interpretation of the samples.Several key parameters of shale oil are projected to data sets with low dimensions in each shale oil facies.Furthermore,the posterior distribution of different shale oil facies is built based on the classification of each shale oil facies.Various key physical parameters of shale oil facies are inversed by the Bayesian method,and important elastic properties are extracted from the elastic impedance inversion(EVA-DSVD method).The method proposed in this paper has been successfully used to delineate the sweet spots of shale oil reservoirs with multiple attributes from the real pre-stack seismic data sets and is validated by the well log data.

Multi-task Joint Sparse Representation Classification Based on Fisher Discrimination Dictionary Learning

Recently,sparse representation classification(SRC)and fisher discrimination dictionary learning(FDDL)methods have emerged as important methods for vehicle classification.In this paper,inspired by recent breakthroughs of discrimination dictionary learning approach and multi-task joint covariate selection,we focus on the problem of vehicle classification in real-world applications by formulating it as a multi-task joint sparse representation model based on fisher discrimination dictionary learning to merge the strength of multiple features among multiple sensors.To improve the classification accuracy in complex scenes,we develop a new method,called multi-task joint sparse representation classification based on fisher discrimination dictionary learning,for vehicle classification.In our proposed method,the acoustic and seismic sensor data sets are captured to measure the same physical event simultaneously by multiple heterogeneous sensors and the multi-dimensional frequency spectrum features of sensors data are extracted using Mel frequency cepstral coefficients(MFCC).Moreover,we extend our model to handle sparse environmental noise.We experimentally demonstrate the benefits of joint information fusion based on fisher discrimination dictionary learning from different sensors in vehicle classification tasks.

Coal–rock interface detection on the basis of image texture features

Based on the stability and inequality of texture features between coal and rock,this study used the digital image analysis technique to propose a coal–rock interface detection method.By using gray level co-occurrence matrix,twenty-two texture features were extracted from the images of coal and rock.Data dimension of the feature space reduced to four by feature selection,which was according to a separability criterion based on inter-class mean difference and within-class scatter.The experimental results show that the optimized features were effective in improving the separability of the samples and reducing the time complexity of the algorithm.In the optimized low-dimensional feature space,the coal–rock classifer was set up using the fsher discriminant method.Using the 10-fold cross-validation technique,the performance of the classifer was evaluated,and an average recognition rate of 94.12%was obtained.The results of comparative experiments show that the identifcation performance of the proposed method was superior to the texture description method based on gray histogram and gradient histogram.

New Method for Multivariate Statistical Process Monitoring

A new method using discriminant analysis and control charts is proposed for monitoring multivariate process operations more reliably.Fisher discriminant analysis （FDA） is used to derive a feature discriminant direction （FDD） between each normal and fault operations,and each FDD thus decided constructs the feature space of each fault operation.Individuals control charts （XmR charts） are used to monitor multivariate processes using the process data projected onto feature spaces.Upper control limit （UCL） and lower control limit （LCL） on each feature space from normal process operation are calculated for XmR charts,and are used to distinguish fault from normal.A variation trend on an XmR chart reveals the type of relevant fault operation.Applications to Tennessee Eastman simulation processes show that this proposed method can result in better monitoring performance than principal component analysis （PCA）-based methods and can better identify step type faults on XmR charts.

Target detection and recognition in SAR imagery based on KFDA

Current research on target detection and recognition from synthetic aperture radar （SAR） images is usually carried out separately. It is difficult to verify the ability of a target recognition algorithm for adapting to changes in the environment. To realize the whole process of SAR automatic target recognition （ATR）, es- pecially for the detection and recognition of vehicles, an algorithm based on kernel fisher discdminant analysis （KFDA） is proposed. First, in order to make a better description of the difference be- tween the background and the target, KFDA is extended to the detection part. Image samples are obtained with a dual-window approach and features of the inner and outer window samples are extracted by using KFDA. The difference between the features of inner and outer window samples is compared with a threshold to determine whether a vehicle exists. Second, for the target area, we propose an improved KFDA-IMED （image Euclidean distance） combined with a support vector machine （SVM） to recognize the vehicles. Experimental results validate the performance of our method. On the detection task, our proposed method obtains not only a high detection rate but also a low false alarm rate without using any prior information. For the recognition task, our method overcomes the SAR image aspect angle sensitivity, reduces the requirements for image preprocessing and improves the recogni- tion rate.

Financial crisis early-warning model of listed companies based on predicted value

To establish a financial early-warning model with high accuracy of discrimination and achieve the aim of long-term prediction, principal component analysis (PCA), Fisher discriminant, together with grey forecasting models are used at the same time. 110 A-share companies listed on the Shanghai and Shenzhen stock exchange are selected as research samples. And 10 extractive factors with 89.746% of all the original information are determined by applying PCA, which obtains the goal of dimension reduction without information loss. Based on the index system, the early-warning model is constructed according to the Fisher rules. And then the GM(1,1) is adopted to predict financial ratios in 2004, according to 40 testing samples from 2000 to 2003. Finally, two different methods, a self-validated and a forecasting-validated, are used to test the validity of the financial crisis warning model. The empirical results show that the model has better predictability and feasibility, and GM(1,1) contributes to the ability to make long-term predictions.

Hydrogeochemical Characteristics and Groundwater Inrush Source Identification for a Multi-aquifer System in a Coal Mine

Correct identification of water inrush sources is particularly important to prevent and control mine water disasters.Hydrochemical analysis,Fisher discriminant analysis,and geothermal verification analysis were used to identify and verify the water sources of the multi-aquifer groundwater system in Gubei coal mine,Anhui Province,North China.Results show that hydrochemical water types of the Cenozoic top aquifer included HCO3-Na+K-Ca,HCO3-Na+K-Mg and HCO3-Na+K,and this aquifer was easily distinguishable from other aquifers because of its low concentration of Na++K+and Cl-.The Cenozoic middle and bottom aquifers,the Permian fissure aquifer,and the Taiyuan and Ordovician limestone aquifers were mainly characterized by the Cl-Na+K and SO4-Cl-Na+K or HCO3-Cl-Na+K water types,and their hydrogeochemistries were similar.Therefore,water sources could not be identified via hydrochemical analysis.Fisher model was established based on the hydrogeochemical characteristics,and its discrimination rate was 89.19%.Fisher discrimination results were improved by combining them with the geothermal analysis results,and this combination increased the identification rate to 97.3%and reasonably explained the reasons behind two water samples misjudgments.The methods described herein are also applicable to other mines with similar geological and hydrogeological conditions in North China.

DISCRIMINATIVE ANALYSIS OF FUNCTIONAL NEAR-INFRARED SPECTROSCOPY SIGNALS FOR DEVELOPMENT OF NEUROIMAGING BIOMARKERS OF ELDERLY DEPRESSION

Functional near-infrared spectroscopy(fNIRS)is a neuroimaging technology which is suitable for psychiatric patients.Several fNIRS studies have found abnormal brain activations during cognitive tasks in elderly depression.In this paper,we proposed a discriminative model of multivariate pattern classification based on fNIRS signals to distinguish elderly depressed patients from healthy controls.This model used the brain activation patterns during a verbal fluency task as features of classification.Then Pseudo-Fisher Linear Discriminant Analysis was performed on the feature space to generate discriminative model.Using leave-one-out(LOO)cross-validation,our results showed a correct classification rate of 88%.The discriminative model showed its ability to identify people with elderly depression and suggested that fNIRS may be an efficient clinical tool for diagnosis of depression.This study may provide the first step for the development of neuroimaging biomarkers based on fNIRS in psychiatric disorders.

Joint global constraint and Fisher discrimination based multi-layer dictionary learning for image classification

A multi-layer dictionary learning algorithm that joints global constraints and Fisher discrimination(JGCFD-MDL)for image classification tasks was proposed.The algorithm reveals the manifold structure of the data by learning the global constraint dictionary and introduces the Fisher discriminative constraint dictionary to minimize the intra-class dispersion of samples and increase the inter-class dispersion.To further quantify the abstract features that characterize the data,a multi-layer dictionary learning framework is constructed to obtain high-level complex semantic structures and improve image classification performance.Finally,the algorithm is verified on the multi-label dataset of court costumes in the Ming Dynasty and Qing Dynasty,and better performance is obtained.Experiments show that compared with the local similarity algorithm,the average precision is improved by 3.34%.Compared with the single-layer dictionary learning algorithm,the one-error is improved by 1.00%,and the average precision is improved by 0.54%.Experiments also show that it has better performance on general datasets.

Training SVMs on a bound vectors set based on Fisher projection

Standard support vector machines （SVMs） train- ing algorithms have O（l3） computational and O（l2） space complexities, where l is the training set size. It is thus com- /putationally infeasible on very large data sets.To alleviate the Computational burden in SVM training, we propose an algo- rithm to train SVMs on a bound vectors set that is extracted based on Fisher projection. For linear separate problems, we use linear Fisher discriminant to compute the projection line, while for non-linear separate problems, we use kernel Fisher discriminant to compute the projection line. For each case, we select a certain ratio samples whose projections are adja- cent to those of the other class as bound vectors. Theoretical analysis shows that the proposed algorithm is with low com- putational and space complexities.Extensive experiments on several classification benchmarks demonstrate the effective- ness of our approach.

KFDA and clustering based multiclass SVM for intrusion detection

To improve the classification accuracy and reduce the training time, an intrusion detection technology is proposed, which combines feature extraction technology and multiclass support vector machine （SVM） classification algorithm. The intrusion detection model setup has two phases. The first phase is to project the original training data into kernel fisher discriminant analysis （KFDA） space. The second phase is to use fuzzy clustering technology to cluster the projected data and construct the decision tree, based on the clustering results. The overall detection model is set up based on the decision tree. Results of the experiment using knowledge discovery and data mining （KDD） from 99 datasets demonstrate that the proposed technology can be an an effective way for intrusion detection.

Influences of drought on the stability of an alpine meadow ecosystem

Drought plays a prominent role in affecting ecosystem stability and ecosystem productivity.Based on eddy covariance and climatic observations during 2012-2020,the Fisher discriminant analysis method was employed to accurately detect drought occurrences.Furthermore,the ecosystem water sensitivity and its resistance to drought were quantified to evaluate the ecosystem stability.The results showed that the alpine meadow suffered drought most frequently at the beginning of the growing seasons.However,drought during the peak growing seasons reduced the gross primary productivity(GPP)the most,by 30.5±15.2%.In the middle of the peak growing seasons,the ecosystem water sensitivity was weak,and thus,the resistance to drought was strong,which resulted in high ecosystem stability.At the beginning and end of the peak growing seasons,the ecosystem stability was relatively weak.Ecosystem stability was positively related to the corresponding multiyear average soil water content(SWC_(ave)).However,drought occurring during high SWC_(ave)periods led to larger reductions in GPP,which indicated that the inhibitory effects of drought on ecosystems were more dependent on the occurrence time of droughts than on ecosystem stability.

Soil liquefaction assessment by using hierarchical Gaussian Process model with integrated feature and instance based domain adaption for multiple data sources

For soil liquefaction prediction from multiple data sources,this study designs a hierarchical machine learning model based on deep feature extraction and Gaussian Process with integrated domain adaption techniques.The proposed model first combines deep fisher discriminant analysis(DDA)and Gaussian Process(GP)in a unified framework,so as to extract deep discriminant features and enhance the model performance for classification.To deliver fair evalu-ation,the classifier is validated in the approach of repeated stratified K-fold cross validation.Then,five different data resources are presented to further verify the model’s robustness and generality.To reuse the gained knowledge from the existing data sources and enhance the generality of the predictive model,a domain adaption approach is formu-lated by combing a deep Autoencoder with TrAdaboost,to achieve good performance over different data records from both the in-situ and laboratory observations.After comparing the proposed model with classical machine learn-ing models,such as supported vector machine,as well as with the state-of-art ensemble learning models,it is found that,regarding seismic-induced liquefaction prediction,the predicted results of this model show high accuracy on all datasets both in the repeated cross validation and Wilcoxon signed rank test.Finally,a sensitivity analysis is made on the DDA-GP model to reveal the features that may significantly affect the liquefaction.

A model for discrimination and prediction of mental workload of aircraft cockpit display interface

With respect to the ergonomic evaluation and optimization in the mental task design of the aircraft cockpit display interface, the experimental measurement and theoretical modeling of mental workload were carried out under flight simulation task conditions using the performance evaluation, subjective evaluation and physiological measurement methods. The experimental results show that with an increased mental workload, the detection accuracy of flight operation significantly reduced and the reaction time was significantly prolonged; the standard deviation of R-R intervals（SDNN） significantly decreased, while the mean heart rate exhibited little change; the score of NASA_TLX scale significantly increased. On this basis, the indexes sensitive to mental workload were screened, and an integrated model for the discrimination and prediction of mental workload of aircraft cockpit display interface was established based on the Bayesian Fisher discrimination and classification method. The original validation and cross-validation methods were employed to test the accuracy of the results of discrimination and prediction of the integrated model, and the average prediction accuracies determined by these two methods are both higher than 85%. Meanwhile, the integrated model shows a higher accuracy in discrimination and prediction of mental workload compared with single indexes. The model proposed in this paper exhibits a satisfactory coincidence with the measured data and could accurately reflect the variation characteristics of the mental workload of aircraft cockpit display interface, thus providing a basis for the ergonomic evaluation and optimization design of the aircraft cockpit display interface in the future.

Plantar ROI Characterization during the Stance Phase of Gait Based on a Low-cost Pressure Acquisition Platform

Plantar Region of Interest （ROI） detection is important for the early diagnosis and treatment ofmorphologic defects of the foot and foot bionic research. Conventional methods have employed complex procedures and expensive instruments which prohibit their widespread use in healthcare. In this paper an automatic plantar ROIs detection method using a customized low-cost pressure acquisition device is proposed. Plantar pressure data and 3D motion capture data were collected from 28 subjects （14 healthy subjects and 14 subjects with hallux valgus）. The maximal inter-frame difference during the stance phase was calculated. Consequently, the ROIs were defined by the first-order difference in combination with prior anatomic knowl- edge. The anatomic locations were determined by the maximal inter-frame difference and second maximal inter-frame differ- ence, which nearly coincided. Our system can achieve average recognition accuracies of 92.90%, 89.30%, 89.30%, 92.90%, 92.90%, and 89.30% for plantar ROIs hallux and metatarsi I-V, respectively, as compared with the annotations using the 3D motion capture system. The maximal difference of metatarsus heads II-V, and the impulse of the medial and lateral heel features made a significant contribution to the classification ofhallux valgus and healthy subjects with ≥ 80% sensitivity and specificity. Furthermore, the plantar pressure acquisition system is portable and convenient to use, thus can be used in home- or commu- nity-based healthcare applications.

Noninvasive Surface Detection of Papillary Thyroid Carcinoma by Fourier Transform Infrared Spectroscopy

Previously Fourier transform infrared（FTIR） spectroscopy has been applied to detecting thyroid cancer during operations and to discriminating cervical metastatic ones from non-metastatic lymph nodes. This study explored the possibility of establishing a sensitive, accurate and noninvasive screen or diagnosis by preoperative FTIR spectroscopy. 111 patients undergone a thyroid operation and 50 healthy volunteers were enrolled in the study. The FTIR spectra were obtained by two mid-infrared optical fibers with an attenuated total reflectance（ATR） probe closely contacting the subjects＇ skin on the thyroid nodules. The FTIR spectra obtained from normal thyroid, nodular goiter（NG） and papillary thyroid carcinoma（PTC） patients were compared. A Fisher＇s discriminant analysis was created based on these data. There were 41 PTC patients and 70 NG patients according to their histopathological examinations. A total of 23（of 39） parameters were statistically different among the three groups（P〈0.05）. The Fi300 and F1080 parameters were significantly different between the three groups. In total, 9 out of 39 FTIR parameters were selected as independent factors by the Wilks＇ lambda stepwise discriminant analysis. The discrimination accuracy of papillary thyroid carcinoma in the three groups was 88.8%. Surface detection of PTC by FTIR spectroscopy is feasible. FTIR spectroscopy can be used for rapid and noninvasive PTC screen and auxiliary diagnosis.

Palm vein recognition method based on fusion of local Gabor histograms

Gabor features have been shown to be effective for palm vein recognition. This paper presents a novel feature representation method, implementing the fusion of local Gabor histograms （FLGH）, in order to improve the accuracy of palm vein recognition systems. A new local descriptor called local Gabor principal differences patterns （LGPDP） encodes the Gabor magnitude using the local maximum difference （LMD） operator. The corresponding Gabor phase patterns are encoded by local Gabor exclusive OR （XOR） patterns （LGXP）. Fisher＇s linear discriminant （FLD） method is then implemented to reduce the dimensionality of the feature representation. Low-dimensional Gabor magnitude and phase feature vectors are finally fused to enhance accuracy. Experimental results from Institute of Automation, Chinese Academy of sciences （CASIA） database show that the proposed FLGH method achieves better performance by utilizing score-level fusion. The equal error rate （EER） is 0.08%, which outperforms other conventional palm vein recognition methods （EER range from 2.87% to 0.16%）, e.g., the Laplacian palm, minutiae feature, Hessian phase, Eigenvein, local invariant features, mutual foreground local binary patterns （LBP）, and multi-sampling feature fusion methods.

Kernel feature extraction methods observed from the viewpoint of generating-kernels

This paper introduces an idea of generating a kernel from an arbitrary function by embedding the training samples into the function.Based on this idea,we present two nonlinear feature extraction methods:generating kernel principal component analysis(GKPCA)and generating kernel Fisher discriminant(GKFD).These two methods are shown to be equivalent to the function-mapping-space PCA(FMS-PCA)and the function-mapping-space linear discriminant analysis(FMS-LDA)methods,respectively.This equivalence reveals that the generating kernel is actually determined by the corresponding function map.From the generating kernel point of view,we can classify the current kernel Fisher discriminant(KFD)algorithms into two categories:KPCA+LDA based algorithms and straightforward KFD(SKFD)algorithms.The KPCA+LDA based algorithms directly work on the given kernel and are not suitable for non-kernel functions,while the SKFD algorithms essentially work on the generating kernel from a given symmetric function and are therefore suitable for non-kernels as well as kernels.Finally,we outline the tensor-based feature extraction methods and discuss ways of extending tensor-based methods to their generating kernel versions.