Linear Discriminant Analysis Approach Research Articles

Model-based impending lithium battery terminal voltage collapse detection via data-driven and machine learning approaches

Lithium battery is an important power source of an electrical vehicle (EV). Practically, when a battery is about to fail, it needs to be removed from the load because keeping it connected can lead to permanent damage. Hence, it is important to detect battery failure to sustain the lifespan of the battery and avoid safety issues which will contribute to the sustainability of the EV. However, determining the effective disconnecting or discharging moment of the battery remains a challenging issue in EV applications. In order to solve the abovementioned problem, a control framework and maximum likelihood estimation are proposed to estimate the parameters of a battery model. In addition, both the sparse representation and dynamic mode decomposition (DMD) approaches are applied to protect the physical battery unit from a failure scenario. For comparison purposes, the proposed framework is compared to a Lyapunov-based detection approach along with neural network (NN) and linear discriminant analysis (LDA). Moreover, several state estimation algorithms are applied to estimate battery state of charge (SOC) at each time step: extended Kalman filter, extended Kalman smooth variable structure filter, and cubature Kalman filter. Finally, the experimental results showed that the proposed DMD approach outperforms the sparse representation, NN, LDA, and Lyapunov-based approaches in terms of detection accuracy. Moreover, the proposed DMD strategy is more robust towards the inaccuracy of the estimated SOC. Besides that, the proposed battery model parameter estimation approach exhibited fast processing time; therefore, it is a reliable choice for recomputing the model parameters from time to time to compensate aging effect. An autonomous unmanned aerial vehicle (UAV) was simulated as a proof-of-concept in a MATLAB environment to verify the detection performance of the proposed methods. Both actual and UAV results showed that the DMD demonstrated more robust detection performance than other methods in terms of processing time and detection accuracy.

An energy-aware heart disease prediction system using ESMO and optimal deep learning model for healthcare monitoring in IoT

ABSTRACT: The Internet of Things (IoT), which provides seamless connectivity between people and things, improves our quality of life. In the medical field, predictive analytics can help transform a reactive healthcare (HC) strategy into a proactive one. The HC industry embraces cutting-edge artificial intelligence and machine learning (ML) technologies. ML’s area of deep learning has the revolutionary potential to reliably analyze massive volumes of data quickly, produce insightful revelations and solve challenging issues. This article proposes an energy-aware heart disease prediction (HDP) system based on enhanced spider monkey optimization (ESMO) and a weight-optimized neural network for an IoT-based HC environment. The proposed work consists of two essential phases: energy-efficient data transmission and HDP. In energy-efficient transmission, the cluster leaders are optimally selected using ESMO and the cluster formation is done based on Euclidean distance. In HDP, the patient data are collected from the dataset, and essential features are extracted. After that, the dimensionality reduction is carried out using the modified linear discriminant analysis approach to reduce over-fitting issues. Finally, the HDP uses the enhanced Archimedes weight-optimized deep neural network (EAWO-DNN). The simulation findings demonstrate that the proposed optimal clustering mechanism enhances the network’s lifespan by consuming minimal energy compared to the existing techniques. Also, the proposed EAWO-DNN classifier achieves higher prediction accuracy, precision, recall and f-measure than the conventional methods for predicting heart disease in IoT. Communicated by Ramaswamy H. Sarma

Machine-Learning Aided NO2 Discrimination with an Array of Graphene Chemiresistors Covalently Functionalized by Diazonium Chemistry.

Boosted by the emerging need for highly integrated gas sensors in IoT ecosystems, electronic noses (e-noses) are gaining interest for the detection of specific molecules over a background of interfering gases. The sensing of nitrogen dioxide (NO2) is particularly relevant for applications in environmental monitoring and precision medicine. Here we present an easy and efficient functionalization procedure to covalently modify graphene layers, taking advantage of diazonium chemistry. Separate graphene layers were functionalised with one of three different aryl rings 4-nitrophenyl, 4-carboxyphenyl, and 4-bromophenyl). The distinct mod(ified graphene layers were assembled with a pristine layer into an e-nose for NO2 discrimination. A remarkable sensitivity to NO2 is demonstrated through exposures to gaseous solutions with NO2 concentrations in the 1-10 ppm range at room temperature. Then, the discrimination capability of the sensor array is tested by carrying out exposures to several interfering gases and analyzing the data through multivariate statistical analysis. This analysis shows that the e-nose can discriminate NO2 among all the interfering gases in a two-dimensional principal component analysis space. Finally, the e-nose is trained to accurately recognize NO2 contributions with a linear discriminant analysis approach, thus providing a metric for discrimination assessment with a prediction accuracy above 95%.

Geographical origin traceability of mulberry leaves using stable hydrogen, oxygen, and carbon isotope ratios.

Geographical discrimination of mulberry leaves is very important for their efficacy and quality as a traditional Chinese medicine. Stable hydrogen, oxygen, and carbon isotope ratios were measured in 292 mulberry leaves collected at 2 growth stages in 2 seasons from 8 regions of China. A stepwise linear discriminant analysis (LDA) approach were proposed to combine with stable isotope technology to tracing the origin of mulberry leaves. The results showed that leaves sampled in autumn were extremely depleted in 2H and 18O and slightly enriched in 13C compared with leaves sampled in summer, correlated with the effect of season, transpiration and photorespiration on stable isotopes. δ2H and δ18O of the leaves were enriched during the growth process. The overall discrimination accuracy of the autumn tender model was 81%, demonstrating that analysis of δ2H, δ18O, and δ13C is a promising technique for tracing the geographical origin of mulberry leaves, although season, growth stage and number of samples affect the accuracy of discrimination.

Spatial linear discriminant analysis approaches for remote-sensing classification

Linear Discriminant Analysis (LDA) is a popular and simple classification tool that often outperforms more sophisticated modern machine learning techniques in remote sensing. We introduce a novel LDA method that uses spatial autocorrelation of all pixels of an object to be classified but also of other objects of the training set that are spatially close to improve classification performance. To simplify spatial modelling and model fitting, the methodology is applied to the transformed feature vectors. We term this method conditional spatial LDA. Much alike universal Kriging in geostatistical interpolation, the combined use of feature data and conditioning on labelled training data in conditional spatial LDA was best able to exploit the available geospatial data. The method is illustrated on a crop classification case study from the Aconcagua agricultural region in central Chile.

Measures of spatial heterogeneity in the liver tissue micro-environment as predictive factors for fibrosis score

The organization and interaction between hepatocytes and other hepatic non-parenchymal cells plays a pivotal role in maintaining normal liver function and structure. Although spatial heterogeneity within the tumor micro-environment has been proven to be a fundamental feature in cancer progression, the role of liver tissue topology and micro-environmental factors in the context of liver damage in chronic infection has not been widely studied yet. We obtained images from 110 core needle biopsies from a cohort of chronic hepatitis B patients with different fibrosis stages according to METAVIR score. The tissue sections were immunofluorescently stained and imaged to determine the locations of CD45 positive immune cells and HBsAg-negative and HBsAg-positive hepatocytes within the tissue. We applied several descriptive techniques adopted from ecology, including Getis–Ord, the Shannon Index and the Morisita–Horn Index, to quantify the extent to which immune cells and different types of liver cells co-localize in the tissue biopsies. Additionally, we modeled the spatial distribution of the different cell types using a joint log-Gaussian Cox process and proposed several features to quantify spatial heterogeneity. We then related these measures to the patient fibrosis stage by using a linear discriminant analysis approach. Our analysis revealed that the co-localization of HBsAg-negative hepatocytes with immune cells and the co-localization of HBsAg-positive hepatocytes with immune cells are equally important factors for explaining the METAVIR score in chronic hepatitis B patients. Moreover, we found that if we allow for an error of 1 on the METAVIR score, we are able to reach an accuracy of around 80%. With this study we demonstrate how methods adopted from ecology and applied to the liver tissue micro-environment can be used to quantify heterogeneity and how these approaches can be valuable in biomarker analyses for liver topology.

Complexity analysis of electrical activity during endocardial and epicardial biventricular mapping of ventricular fibrillation.

Ventricular fibrillation (VF) is a lethal cardiac arrhythmia that is a significant cause of sudden cardiac death. Comprehensive studies of spatiotemporal characteristics of VF in situ are difficult to perform with current mapping systems and catheter technology. The goal of this study was to develop a computational approach to characterize VF using a commercially available technology in a large animal model. Prior data suggests that characterization of spatiotemporal organization of electrical activity during VF can be used to provide better mechanistic understanding and potential ablation targets to modify VF and its substrate. We therefore evaluated intracardiac electrograms during biventricular mapping of the endocardium (ENDO) and epicardium (EPI) in acute canine studies. To develop thresholds for organized and disorganized activity, a linear discriminant analysis (LDA)-based approach was performed to the known organized and disorganized activities recorded in ex vivo Langendorff-perfused rat and rabbit hearts using optical mapping experiments. Several frequency- and time-domain approaches were used as individual and paired features to identify the optimal thresholds for the LDA approach. Subsequently, VF was sequentially mapped in 4 canine hearts, using the CARTO mapping system with a multipolar mapping catheter in the ENDO left and right ventricles and EPI to capture the progression of VF at 3 discrete post-induction time intervals: VF period 1 (just after induction of VF to 15 min), VF period 2 (15 to 30 min), and VF period 3 (30 to 45 min). The developed LDA model, cycle lengths (CL), and regularity indices (RI) were applied to all recorded intracardiac electrograms to quantify the spatiotemporal organization of VF in canine hearts. We demonstrated the presence of organized activity in the EPI as VF progresses, in contrary to the ENDO, where the activity stays disorganized. The shortest CL always occurred in the ENDO, especially the RV, indicating a faster VF activity. The highest RI was found in the EPI in all hearts for all VF stages, indicating spatiotemporal consistency of RR intervals. We identified electrical organization and spatiotemporal differences throughout VF in canine hearts from induction to asystole. Notably, the RV ENDO is characterized by a high level of disorganization and faster VF frequency. In contrast, EPI has a high spatiotemporal organization of VF and consistently long RR intervals.

Nondestructive detection of adulterated wolfberry (Lycium Chinense) fruits based on hyperspectral imaging technology

AbstractIn order to detect adulterants on Lycium Chinense species effectively, a rapid, clean, and nondestructive detection method based on hyperspectral imaging (HSI) technology was conducted in a wavelength range of 400.68–1001.60 nm. Industrial sulfur particles were chosen as a dye to prepare three groups of adulterated L. Chinense samples as the research object. The whole L. Chinense was considered the region of interest. First, a multiple scatter correction (MSC) method was used to preprocess spectra data. The competitive adaptive reweighted sampling (CARS) and linear discriminant analysis approaches were contrasted for optimal extraction of wavelengths characteristic. Then, two models were established: K‐nearest neighbor (KNN) and support vector machine (SVM). Furthermore, the performance accuracies of KNN and SVM models were compared. According to the outcomes, the SVM model built on CARS provided the best classification impact. The accuracy for the prediction set was 98.75%, and the accuracy for the training set was 100%. Also, the kernel parameters c and g of the SVM model were enhanced by genetic algorithm (GA) optimization. The values parameters (c, g) were set at 14.975 and 0.224, respectively, and the results improved by 1.25% at an elapsed time of 1.887 s, with the accuracy reaching 100% on both training and test sets. This study aimed to detect and classify sulfur‐adulterated wolfberries using an improved SVM and HSI. Finally, the results demonstrate that a combination of HSI and the CARS‐GA‐SVM model could be used for the rapid detection of foreign entities' in wolfberry fruits.Practical applicationsDried wolfberry adulteration has a direct link to the overall quality of the fruits, and potentially compromises the health of the fruits consumers. The traditional methods of testing adulterants on Lycium Chinense are arduous, require a lot of time, and are highly impacted by biased elements, necessitating new techniques. HSI technology, on the other hand, is nondestructive, quick/fast, accurate, subjective, reproducible, and pollution‐free. The study findings proved to be recommendable for initiating a feasible mobile system for rapidly detecting adulteration on L. Chinense.

A Chemiresistor Sensor Array Based on Graphene Nanostructures: From the Detection of Ammonia and Possible Interfering VOCs to Chemometric Analysis.

Sensor arrays are currently attracting the interest of researchers due to their potential of overcoming the limitations of single sensors regarding selectivity, required by specific applications. Among the materials used to develop sensor arrays, graphene has not been so far extensively exploited, despite its remarkable sensing capability. Here we present the development of a graphene-based sensor array prepared by dropcasting nanostructure and nanocomposite graphene solution on interdigitated substrates, with the aim to investigate the capability of the array to discriminate several gases related to specific applications, including environmental monitoring, food quality tracking, and breathomics. This goal is achieved in two steps: at first the sensing properties of the array have been assessed through ammonia exposures, drawing the calibration curves, estimating the limit of detection, which has been found in the ppb range for all sensors, and investigating stability and sensitivity; then, after performing exposures to acetone, ethanol, 2-propanol, sodium hypochlorite, and water vapour, chemometric tools have been exploited to investigate the discrimination capability of the array, including principal component analysis (PCA), linear discriminant analysis (LDA), and Mahalanobis distance. PCA shows that the array was able to discriminate all the tested gases with an explained variance around 95%, while with an LDA approach the array can be trained to accurately recognize unknown gas contribution, with an accuracy higher than 94%.

Landmark Recognition Model for Smart Tourism using Lightweight Deep Learning and Linear Discriminant Analysis

Scene recognition algorithm is crucial for landmark recognition model development. Landmark recognition model is one of the main modules in the intelligent tour guide system architecture for the use of smart tourism industry. However, recognizing the tourist landmarks in the public places are challenging due to the common structure and the complexity of scene objects such as building, monuments and parks. Hence, this study proposes a super lightweight and robust landmark recognition model by using the combination of Convolutional Neural Network (CNN) and Linear Discriminant Analysis (LDA) approaches. The landmark recognition model was evaluated by using several pretrained CNN architectures for feature extraction. Then, several feature selections and machine learning algorithms were also evaluated to produce a super lightweight and robust landmark recognition model. The evaluations were performed on UMS landmark dataset and Scene-15 dataset. The results from the experiments have found that the Efficient Net (EFFNET) with CNN classifier are the best feature extraction and classifier. EFFNET-CNN achieved 100% and 94.26% classification accuracy on UMS-Scene and Scene-15 dataset respectively. Moreover, the feature dimensions created by EFFNet are more compact compared to the other features and even have significantly reduced for more than 90% by using Linear Discriminant Analysis (LDA) without jeopardizing classification performance but yet improved its performance.

Discrimination of three varieties of Codonopsis Radix based on fingerprint profiles of oligosaccharides by high performance liquid chromatography- evaporative light scattering detector combined with multivariate analysis

Codonopsis Radix (CR) is a plant that is important in the practice of traditional Chinese medicine (TCM). The Chinese Pharmacopoeia 2020 records dried roots prepared from three varieties of Campanulaceae plants under the designation CR (“Dang-shen” in Chinese), including Codonopsis pilosula (Franch.) Nannf (C. pilosula), Codonopsis pilosula Nannf.var.modesta (Nannf.) L81. T. Shen (C. pilosula var. modesta) and Codonopsis tangshen Oliv (C. tangshen). As major constituents of CR, oligosaccharides might contribute to its clinical efficacy except for other known active compounds, yet the differences in the oligosaccharide profiles of these three varieties of CR remain incompletely understood. In the present study, 135 samples from these different CR varieties were harvested, and oligosaccharide fingerprints for these samples were characterized via HPLC-ELSD, with 19 common peaks being matched. Oligosaccharides were further identified through the combination of electrospray ionization MS/MS (ESI-MS/MS) with nuclear magnetic resonance (NMR). Principal component analysis and linear discriminant analysis (LDA) approaches were then used to compare the oligosaccharide profiles of these three CR varieties. These analyses ultimately revealed that CR was compared with principal component analysis (PCA) and linear discriminant (LDA) methods. The analyses ultimately revealed that these CR samples contained high levels of inulin- and levan-type fructooligosaccharides (FOS), with variations in the relative levels of these FOS compounds among the three analyzed CR varieties. Through the combined analysis of oligosaccharide fingerprints and LDA results, it was possible to differentiate among these CR varieties, with an accurate classification rate of 96.3% and a cross-validation rate of 95.6%. Together, these results highlight a valuable approach to the classification and identification of different CR varieties.

Introducing block-Toeplitz covariance matrices to remaster linear discriminant analysis for event-related potential brain–computer interfaces

Objective. Covariance matrices of noisy multichannel electroencephalogram (EEG) time series data provide essential information for the decoding of brain signals using machine learning methods. However, small datasets and high dimensionality make it hard to estimate these matrices. In brain–computer interfaces (BCI) based on event-related potentials (ERP) and a linear discriminant analysis (LDA) classifier, the state of the art covariance estimation uses shrinkage regularization. As this is a general covariance regularization approach, we aim at improving LDA further by better exploiting the domain-specific characteristics of the EEG to regularize the covariance estimates. Approach. We propose to enforce a block-Toeplitz structure for the covariance matrix of the LDA, which implements an assumption of signal stationarity in short time windows for each channel. Main results. An offline re-analysis of data collected from 213 subjects under 13 different event-related potential BCI protocols showed a significantly increased binary classification performance of this ‘ToeplitzLDA’ compared to shrinkage regularized LDA (up to 6 AUC points, p < 0.001) and Riemannian classification approaches (up to 2 AUC points, p < 0.001). In an unsupervised visual speller application, this improvement would translate to a relative reduction of spelling errors by 81% on average for 25 subjects. Additionally, aside from lower memory and reduced time complexity for LDA training, ToeplitzLDA proves to be robust against drastic increases of the number of temporal features. Significance. The proposed covariance estimation allows BCI researchers to improve classification rates and reduce calibration times of BCI protocols using event-related potentials and thus support the usability of corresponding applications. Its lower computational and memory needs could make it a valuable algorithm especially for mobile BCIs.

Algorithm Symmetric 2-DLDA for Recognizing Handwritten Capital Letters

Statistical pattern recognition is the process of using statistical techniques to obtain information and make informed decisions based on data measurements. It is possible to solve the doubt inherent in the objective function of the 2-Dimension Linear Discriminant Analysis by employing the symmetrical 2-Dimension Linear Discriminant Analysis approach. Symmetrical 2-dimensional linear discriminant analysis has found widespread use as a method of introducing handwritten capital letters. Symmetric 2-DLDA, according to Symmetric 2-DLDA, produces better and more accurate results than Symmetric 2-DLDA. So far, pattern recognition has been based solely on computer knowledge, with no connection to statistical measurements, such as data variation and Euclidean distance, particularly in symmetrical images. As a result, the aim of this research is to create algorithms for recognizing capital letter patterns in a wide range of handwriting. The ADL2-D symmetric method is used in this study as the development of the ADL2-D method. The research results in an algorithm that considers the left and right sides of the image matrix, as opposed to ADL2-D, which does not consider the left and right sides of the image matrix. In pattern recognition, the results with symmetric ADL2-D are more accurate

Forewarning of insect incidence based on weather variables for management of cropping practices in Sugarcane

The early shoot borer, top borer, root borer, internode borer are major insect occurs in most of the sugarcane growing areas of the Gujarat and cause extensive damage to the sugarcane crop, which leads to losses in the crop yield. The weather discrepancies acting an important role in development of sugarcane insect and pest. The proper management of cropping practices may leads to overcome on it. Therefore it need to develop weather based approaches for forewarning the insect incidence which helps to farmers takes timely control measures to reduce the damage and yield losses due to this borer complex. Current study, relationship between insects incidence with weekly average weather parameters has been workout by using Karl-Pearson’s correlation approach on the 18 years of the data (2000-01 to 2017-18) in the Navsari district. The some of the weather variables were found significantly correlated with insect incidence. The multiple linear regression (MLR) and discriminant function analysis approach were adopted for statistical forewarning of the insect incidence. It was observed that MLR technique found better than discriminant function analysis for forecasting of insect incidence for forewarning of early shoot borer at 90 DAP and top shoot borer incidence at 5th month of crop season respectively.

Harvesting Brain Signal Using Machine Learning Methods

Abstract Brain computer interface (BCI) systems are developed in the biomedical engineering fields to increase the quality of life among patients with paralysis and neurological conditions. The development of a six class BCI controller to operate a semi-autonomous mobile robotic arm is presented. The controller uses the following mental tasks: imagined left/right hand squeeze, imagined left/right foot tap, rest, and a physical jaw clench. To design a controller, the locations of active electrodes are verified, and an appropriate machine learning algorithm is determined. Three subjects, ages ranging between 22 and 27, participated in five sessions of motor imagery experiments to record their brainwaves. These recordings were analyzed using event related potential (ERP) plots and topographical maps to determine active electrodes. bcilab was used to train two, three, five, and six class BCI controllers using linear discriminant analysis (LDA) and relevance vector machine (RVM) machine learning methods. The subjects' data were used to compare the two-method's performance in terms of error rate percentage. While a two class BCI controller showed the same accuracy for both methods, the three and five class BCI controllers showed the RVM approach having a higher accuracy than the LDA approach. For the five-class controller, error rate percentage was 33.3% for LDA and 29.2% for RVM. The six class BCI controller error rate percentage for both LDA and RVM was 34.5%. While the percentage values are the same, RVM was chosen as the desired machine learning algorithm based on the trend seen in the three and five class controller performances.

Unlocking Kautsky’s dark box: Development of an optical toxicity classification tool (OPTOX index) with marine diatoms exposed to emerging contaminants

Chlorophyll a induction curves, or Kautsky curves, have been extensively used to study physiological stress conditions in phototrophic organisms, with the analysis of several derived parameters. Nevertheless, these variables use only about 10 % of the information comprised in the complete Kautsky curve dataset, leaving 90 % of the photochemical data within an underutilized dark box, that is not translated into photochemically relevant variables. By observing the variable fluorescence profiles from marine diatoms exposed to a myriad of emerging and classical contaminants, several fluorescence profile alterations were detected, with significant deviations from the control conditions concomitant with the degree of growth inhibition imposed by the chemical stressor. The Linear Discriminant Analysis (LDA) analysis based on the normalized variable chlorophyll a fluorescence profiles revealed a high discriminatory efficiency of the type of contaminant to which the cultures were exposed, indicating that the exposure to different chemical stressors (contaminants) results in specific fluorescence profiles that can be used as descriptors of these exposure conditions. Analysing the individual contaminant LDA analysis, a very low overlap between samples exposed to different concentrations was observed, indicating a high discriminatory power of the variable fluorescence profiles. When evaluating the blind-test classification efficiencies, provided by this contaminant-specific LDA approach, it was possible to observe a high degree of efficiency in almost all contaminants tested, and for most of the concentrations applied. With this in mind, the produced linear discriminants and proportion of traces was used to compute an optical toxicity classification tool - the OPTOX index. The index revealed a high degree of correlation with the growth inhibition observed and/or with the exogenous dose of contaminant applied. The developed OPTOX index, a unifying tool enclosing all the fluorescence data provided by the chlorophyll a induction curve, proved to be an efficient tool to apply in ecotoxicological assays using marine model diatoms with a high degree of reliability for classifying the exposure of the cells to emerging contaminants. Additionally, the data analysis pipeline, as well as the index development methodology here proposed, can be easily transposed to other autotrophic organisms subjected to different ecotoxicological test conditions calibrated and validated against known biochemical or morphological descriptors of stress, integrating this way a large amount of data that was until know completely overlooked and left within an underutilized and undervalued dark box.

Diagnosis of Alzheimer's Disease by Time-Dependent Power Spectrum Descriptors and Convolutional Neural Network Using EEG Signal.

Using strategies that obtain biomarkers where early symptoms coincide, the early detection of Alzheimer's disease and its complications is essential. Electroencephalogram is a technology that allows thousands of neurons with equal spatial orientation of the duration of cerebral cortex electrical activity to be registered by postsynaptic potential. Therefore, in this paper, the time-dependent power spectrum descriptors are used to diagnose the electroencephalogram signal function from three groups: mild cognitive impairment, Alzheimer's disease, and healthy control test samples. The final feature used in three modes of traditional classification methods is recorded: k-nearest neighbors, support vector machine, linear discriminant analysis approaches, and documented results. Finally, for Alzheimer's disease patient classification, the convolutional neural network architecture is presented. The results are indicated using output assessment. For the convolutional neural network approach, the accurate meaning of accuracy is 82.3%. 85% of mild cognitive impairment cases are accurately detected in-depth, but 89.1% of the Alzheimer's disease and 75% of the healthy population are correctly diagnosed. The presented convolutional neural network outperforms other approaches because performance and the k-nearest neighbors' approach is the next target. The linear discriminant analysis and support vector machine were at the low area under the curve values.

Deep Regularized Discriminative Network

Traditional linear discriminant analysis (LDA) approach discards the eigenvalues which are very small or equivalent to zero, but quite often eigenvectors corresponding to zero eigenvalues are the important dimensions for discriminant analysis. We propose an objective function which would utilize both the principal as well as nullspace eigenvalues and simultaneously inherit the class separability information onto its latent space representation. The idea is to build a convolutional neural network (CNN) and perform the regularized discriminant analysis on top of this and train it in an end-to-end fashion. The backpropagation is performed with a suitable optimizer to update the parameters so that the whole CNN approach minimizes the within class variance and maximizes the total class variance information suitable for both multi-class and binary class classification problems. Experimental results on four databases for multiple computer vision classification tasks show the efficacy of our proposed approach as compared to other popular methods.

Application of Artificial Intelligence-Based Classifiers to Predict the Outcome Measures and Stone-Free Status Following Percutaneous Nephrolithotomy for Staghorn Calculi: Cross-Validation of Data and Estimation of Accuracy

Objective: To develop a decision support system (DSS) for the prediction of the postoperative outcome of a kidney stone treatment procedure, particularly percutaneous nephrolithotomy (PCNL) to serve as a promising tool to provide counseling before an operation. Materials and Methods: The overall procedure includes data collection and prediction model development. Pre-/postoperative variables of 100 patients with staghorn calculus, who underwent PCNL, were collected. For feature vector, variables and categories including patient history variables, kidney stone parameters, and laboratory data were considered. The prediction model was developed using machine learning techniques, which include dimensionality reduction and supervised classification. Multiple classifier scheme was used for prediction. The derived DSS was evaluated by running the leave-one-patient-out cross-validation approach on the data set. Results: The system provided favorable accuracy (81%) in predicting the outcome of a treatment procedure. Performance in predicting the stone-free rate with the Minimum Redundancy Maximum Relevance feature (MRMR) treatment extracting top 3 features using Random Forest (RF) was 67%, with MRMR treatment extracting top 5 features using RF was 63%, and with MRMR treatment extracting top 10 features using Decision Tree was 62%. The statistical significance using standard error between the best area under the curves (AUCs) obtained from the Linear Discriminant Analysis (LDA) and MRMR. The results obtained from the LDA approach (0.81 AUC) was statistically significant (p = 0.027, z = 2.21) from the MRMR (0.64 AUC) (p = 0.05). Conclusion: The promising results of the developed DSS could be used in assisting urologists to provide counseling, predict a surgical outcome, and ultimately choose an appropriate surgical treatment for removing kidney stones.

Deep linear discriminant analysis hashing

The conventional supervised hashing methods based on classification do not entirely meet the requirements of the hashing technique; on the other hand, the linear discriminant analysis (LDA) approach does satisfy such demands. In this paper, we propose to perform the LDA objective over deep networks to learn efficient hashing codes in a truly end-to-end fashion. However, a complicated eigenvalue decomposition within each mini-batch in every epoch has to be faced with when simply optimizing the deep network with respect to the LDA objective. Here, the LDA objective is transformed into a simple least-square problem, which naturally overcomes the intractable problems and can be easily solved by an off-the-shelf optimizer. Such deep extension can also overcome the weaknesses of LDA hashing involving the limited linear projection and feature learning. Numerous experiments were conducted on three benchmark datasets. The proposed deep LDA hashing approach exhibits an improvement of nearly 70 points for the CIFAR-10 dataset over the conventional strategy. Additionally, the proposed approach is found to be superior to several state-of-the-art methods for various metrics.