Kernel Support Research Articles

A Memory-Efficient Federated Kernel Support Vector Machine for Edge Devices.

A federated learning (FL) scheme (denoted as Fed-KSVM) is designed to train kernel support vector machines (SVMs) over multiple edge devices with low memory consumption. To decompose the training process of kernel SVM, each edge device first constructs high-dimensional random feature vectors of its local data, and then trains a local SVM model over the random feature vectors. To reduce the memory consumption on each edge device, the optimization problem of the local model is divided into several subproblems. Each subproblem only optimizes a subset of the model parameters over a block of random feature vectors with a low dimension. To achieve the same optimal solution to the original optimization problem, an incremental learning algorithm called block boosting is designed to solve these subproblems sequentially. After training of the local models, the central server constructs a global SVM model by averaging the model parameters of these local models. Fed-KSVM only increases the iterations of training the local SVM models to save the memory consumption, while the communication rounds between the edge devices and the central server are not affected. Theoretical analysis shows that the kernel SVM model trained by Fed-KSVM converges to the optimal model with a linear convergence rate. Because of such a fast convergence rate, Fed-KSVM reduces the communication cost during training by up to 99% compared with the centralized training method. The experimental results also show that Fed-KSVM reduces the memory consumption on the edge devices by nearly 90% while achieving the highest test accuracy, compared with the state-of-the-art schemes.

Dual Kernel Support Vector-based Crossover Red Fox Algorithm: Advancements in Assistive Technology for Hearing-impaired Individuals

Individuals with hearing impairment face several challenges, including difficulties in communication, social interactions, and accessibility to information on various auditory abilities. Innovations range from hearing aids to advanced communication devices and mobile apps. Designing solutions that prioritize user feedback ensures a more inclusive and empowering experience for people with hearing impairment. Assistive technology (AT) endeavors to enhance the daily lives of individuals, fostering greater connectivity, and also plays a crucial role in addressing these challenges. Therefore, an attention dual kernel support vector-based crossover red fox (ADKS-CRF) algorithm is developed for superior performance. This research study proposes a model combining a dual kernel support vector machine with an attention mechanism to implicitly operate in a high-dimensional feature space without computing the transformed vector features. The crossover strategy is incorporated with the red fox optimization algorithm, and the integrated formation of CRF fine-tunes the parameters of the ADKS model, removing the complexity of local optima. This work conducted experiments using raw data from an effective 3D ear acquisition system dataset. Experimental validation is conducted using various evaluation measures to assess effectiveness. The proposed hybrid approach achieves a sensitivity of 97.8%, an F1-score of 97.1%, a specificity of 96.3%, an accuracy of 98.4%, a false alarm rate of 90.8%, and a Matthews correlation coefficient of 97.3%. The comparative analysis evaluates the efficacy of the ADKS-CRF method with various baseline approaches for the development of ATs for hearing-impaired people.

Noise-robust ptychography using dynamic sigmoid-remolding

Ptychography is a promising technique for phase retrieval, allowing for super-resolution imaging with a coherent beam source that shifts. The complex transmission function of illumination and object can be retrieved with the support of a ptychographic iterative kernel. When subjected to noisy datasets, conventional reconstruction algorithms can easily be trapped in local minima or even fail to convergence. The present work proposes a new approach called dynamic sigmoid-remolding ptychographic iterative engine (dsPIE) that relies on a dynamic convex optimization strategy. The dsPIE method is designed to improve the robustness in ptychography against detector noise. Computational and experimental results show that the proposed dsPIE method exhibits high robustness and finer reconstructed stability for mixed detector noises that conventional PIE algorithms typically struggle to converge. This method has important implications for the field of computational imaging in high-noise environments.

Multi-biometric fusion for enhanced human authentication in information security

In the digital age, information security has taken on greater importance, necessitating the development of strong and trustworthy human authentication techniques. Traditional single-factor authentication schemes, such passwords or PINs, are prone to a number of security flaws. Multi-biometric fusion approaches have become a possible remedy to these restrictions. In comparison to other fusion techniques, feature level fusion is a very popular technique. Features are taken from every biometric attribute in this fusion. Then, the retrieved features are concatenated to create a high dimension final feature vector. In this study, we present a novel method for feature-level fusion employing optimal feature level fusion. The essential features are chosen and identified using a Binary chimp optimized adaptive kernel support vector machine (BCO-AKSVM). According to f1-score (99 %), recall (98 %), accuracy (97 %), precision (88 %), and time computation (1000 ms), the experimental results of the suggested method are analyzed. When compared to current methods, it can show that the proposed BCO-AKSVM achieves the highest performance of information security in human biometric authentication. Multi-biometric fusion is anticipated to play a significant role as technology develops in maintaining secure access control and safeguarding sensitive information in numerous sectors.

Predicting positron emission tomography brain amyloid positivity using interpretable machine learning models with wearable sensor data and lifestyle factors

BackgroundDeveloping a screening method for identifying individuals at higher risk of elevated brain amyloid burden is important to reduce costs and burden to patients in clinical trials on Alzheimer’s disease or the clinical setting. We developed machine learning models using objectively measured lifestyle factors to predict elevated brain amyloid burden on positron emission tomography.MethodsOur prospective cohort study of non-demented, community-dwelling older adults aged ≥ 65 years was conducted from August 2015 to September 2019 in Usuki, Oita Prefecture, Japan. One hundred and twenty-two individuals with mild cognitive impairment or subjective memory complaints (54 men and 68 women, median age: 75.50 years) wore wearable sensors and completed self-reported questionnaires, cognitive test, and positron emission tomography imaging at baseline. Moreover, 99 individuals in the second year and 61 individuals in the third year were followed up. In total, 282 eligible records with valid wearable sensors, cognitive test results, and amyloid imaging and data on demographic characteristics, living environments, and health behaviors were used in the machine learning models. Amyloid positivity was defined as a standardized uptake value ratio of ≥ 1.4. Models were constructed using kernel support vector machine, Elastic Net, and logistic regression for predicting amyloid positivity. The mean score among 10 times fivefold cross-validation repeats was utilized for evaluation.ResultsIn Elastic Net, the mean area under the receiver operating characteristic curve of the model using objectively measured lifestyle factors alone was 0.70, whereas that of the models using wearable sensors in combination with demographic characteristics and health and life environment questionnaires was 0.79. Moreover, 22 variables were common to all machine learning models.ConclusionOur machine learning models are useful for predicting elevated brain amyloid burden using readily-available and noninvasive variables without the need to visit a hospital.Trial registrationThis prospective study was conducted in accordance with the Declaration of Helsinki and was approved by the local ethics committee of Oita University Hospital (UMIN000017442). A written informed consent was obtained from all participants. This research was performed based on the Strengthening the Reporting of Observational Studies in Epidemiology reporting guideline.

Feature selection for sky image classification based on self adaptive ant colony system algorithm

Statistical-based feature extraction has been typically used to purpose obtaining the important features from the sky image for cloud classification. These features come up with many kinds of noise, redundant and irrelevant features which can influence the classification accuracy and be time consuming. Thus, this paper proposed a new feature selection algorithm to distinguish significant features from the extracted features using an ant colony system (ACS). The informative features are extracted from the sky images using a Gaussian smoothness standard deviation, and then represented in a directed graph. In feature selection phase, the self-adaptive ACS (SAACS) algorithm has been improved by enhancing the exploration mechanism to select only the significant features. Support vector machine, kernel support vector machine, multilayer perceptron, random forest, k-nearest neighbor, and decision tree were used to evaluate the algorithms. Four datasets are used to test the proposed model: Kiel, Singapore whole-sky imaging categories, MGC Diagnostics Corporation, and greatest common divisor. The SAACS algorithm is compared with six bio-inspired benchmark feature selection algorithms. The SAACS algorithm achieved classification accuracy of 95.64% that is superior to all the benchmark feature selection algorithms. Additionally, the Friedman test and Mann-Whitney <em>U</em> test are employed to statistically evaluate the efficiency of the proposed algorithms.

Sustainability of Transport Sector Companies: Bankruptcy Prediction Based on Artificial Intelligence

Understanding business failure within the transport industry is crucial for formulating an effective competitive policy. Acknowledging the pivotal role of financial stability as a cornerstone of sustainability, this study undertakes a comparative investigation between statistical models forecasting business failure and artificial intelligence-based models within the context of the transport sector. The analysis spans the temporal period from 2014 to 2021 and encompasses a dataset of 4866 companies from four South European countries: Portugal, Spain, France, and Italy. The models created were linear support vector machines (L-SVMs), kernel support vector machines (K-SVMs), k-nearest neighbors (k-NNs), logistic regression (LR), decision trees (DTs), random forests (RFs), extremely random forests (ERFs), AdaBoost, and neural networks (NNs). The models were implemented in Python using the scikit-learn package. The results revealed that most models exhibited high precision and accuracy, ranging from 71% to 73%, with the ERF model outperforming others in both predictive capacity and accuracy. It was also observed that artificial intelligence-based models outperformed statistical models in predicting business failure, with particular emphasis on the AdaBoost and ERF models. Thus, we conclude that the results confirm the hypothesis that the artificial intelligence models were superior in all metrics compared to the results obtained by logistic regression.

An Expert System Based on Data Mining for a Trend Diagnosis of Process Parameters

In order to diagnose abnormal trends in the process parameters of industrial production, the Expert System based on rolling data Kernel Principal Component Analysis (ES-KPCA) and Support Vector Data Description (ES-SVDD) are proposed in this paper. The expert system is capable of identifying large-scale trend changes and abnormal fluctuations in process parameters using data mining techniques, subsequently triggering timely alarms. The system consists of a rule-based assessment of process parameter stability to evaluate whether the process parameters are stable. Also, when the parameters are unstable, the rolling data-based KPCA and SVDD methods are used to diagnose abnormal trends. ES-KPCA and ES-SVDD methods require adjusting seven threshold parameters during the offline parameter adjustment phase. The system obtains the adjusted parameters and performs a real-time diagnosis of process parameters based on the set diagnosis interval during the online diagnosis phase. The ES-KPCA and ES-SVDD methods emphasize the real-time alarms and the first alarm of process parameter abnormal trends, respectively. Finally, the system validates the experimental data from UniSim simulation and a chemical plant. The results show that the expert system has an outstanding diagnostic performance for abnormal trends in process parameters.

Quantitative Modeling of Stemness in Single-Cell RNA Sequencing Data: A Nonlinear One-Class Support Vector Machine Method.

Intratumoral heterogeneity and the presence of cancer stem cells are challenging issues in cancer therapy. An appropriate quantification of the stemness of individual cells for assessing the potential for self-renewal and differentiation from the cell of origin can define a measurement for quantifying different cell states, which is important in understanding the dynamics of cancer evolution, and might further provide possible targeted therapies aimed at tumor stem cells. Nevertheless, it is usually difficult to quantify the stemness of a cell based on molecular information associated with the cell. In this study, we proposed a stemness definition method with one-class Hadamard kernel support vector machine (OCHSVM) based on single-cell RNA sequencing (scRNA-seq) data. Applications of the proposed OCHSVM stemness are assessed by various data sets, including preimplantation embryo cells, induced pluripotent stem cells, or tumor cells. We further compared the OCHSVM model with state-of-the-art methods CytoTRACE, one-class logistic regression, or one-class SVM methods with different kernels. The computational results demonstrate that the OCHSVM method is more suitable for stemness identification using scRNA-seq data.

Unlocking the Potential: A Deep Learning Approach for Objective Screening of AML with NPM1 Mutation Via Holotomography

Introduction: As the clinical significance of genetic mutations becomes clearer, diagnostic classifications are continuously evolving, making judicious decisions about implementing costly genetic testing for diagnosis crucial. Intriguing observations suggest that Myelodysplastic Syndrome (MDS) or MDS/Myeloproliferative Neoplasm with NPM1 mutation can rapidly progress to Acute Myeloid Leukemia (AML), leading to ambiguity in acute leukemia diagnosis. Consequently, this finding has led to ambiguity surrounding the diagnostic criteria for acute leukemia with low blast counts. Holotomography (HT) is a cutting-edge microscope that utilizes refractive index (RI) as a contrast medium. It not only provides 2D or 3D images but also offers numerical information about every pixel of cells, promising a more objective diagnosis. Previous studies have successfully distinguished mature cells and blasts using HT. In this study, our aim is to construct a sophisticated deep learning model using data from HT to predict the presence of NPM1 mutations in blasts. This research endeavor holds the potential to enable early detection of these mutations in hematologic malignancies and facilitate the effective utilization of valuable medical resources. Methods: We utilized HT to analyze blasts of AML with mutated NPM1 (experimental group) and AML not otherwise specified (control group) but exhibiting similar morphological characteristics from May 2021 to May 2022. We analyzed a total of 648 blasts from 15 patients in the experimental group and 762 blasts from 24 patients in the control group. Cell segmentation for Rule-based features was performed using ilastik version 1.3.3 and MATLAB 2022a. After the initial segmentation using ilastik's machine learning pixel classification feature, further refinements were made in MATLAB, based on prior knowledge of the size and topology of each structure. Subsequently, volumetric and morphological information was measured within these segments. The cell data of each patient were divided into a training set and a test set. The deep learning algorithm, built using the training set, was then validated with data from the test set. For the deep learning and prediction tasks, we employed a Convolutional Neural Network algorithm (Figure). The classification process involved utilizing both the Rule-based features and the entire feature set, where a linear kernel Support Vector Machine was used. Additionally, we employed the Ensemble average approach, where multiple cells' scores (numerical values associated with the probabilities of each classification) were averaged, and the classification with the highest score was selected as the final prediction. Finally, the deep learning model was validated using previously unused test set data through the Receiver Operating Characteristic (ROC) curve. Results: The dry mass of the nucleolus was significantly increased in AML, NOS; Exp, 0.29341 ± 0.014499 pg; Control, 0.71184 ± 0.033521 pg ( P<0.05). The dry mass of the cytoplasm was higher in AML with mutated NPM1, showing a higher value than that of the nucleolus; Exp, 45.7334 ± 0.50003 pg; Control, 42.9807 ± 0.63882 pg (P<0.05). When validating the deep learning model constructed based on individual cells, the area under the ROC curve (AUC) was found to be 0.8836. Even within the same individual, the cell morphology can be heterogeneous. Therefore, when the data from 5 cells were treated as a single entity for validating the deep learning model, the AUC was 0.9944. Conclusions: It is widely acknowledged that the NPM1 protein, typically localized in the nucleolus, undergoes relocation to the cytoplasm as a result of NPM1 mutation. In this investigation, we devised an advanced deep learning model leveraging numerical data derived from HT, enabling us to prognosticate variations in protein expression based on NPM1 mutations. The HT numerical data exhibited distinctive variations in both nuclear and cytoplasmic analyses contingent on NPM1 mutations. Given the current uncertainty in leukemia diagnosis, partly attributable to the costly selection of genetic testing, we are optimistic that the integration of HT with our sophisticated deep learning model will pave the way for early diagnosis prediction before conducting additional genetic tests.

Remote sensing-based scene classification by feature fusion and extraction with ensemble classifier employing machine learning approaches

This research focuses on scene segmentation in remotely sensed images within the field of Remote Sensing Image Scene Understanding (RSISU). Leveraging recent advancements in Deep Learning (DL), particularly Residual Neural Networks (RESNET-50 and RESNET-101), and the research proposes a methodology involving feature fusing, extraction, and classification for categorizing remote sensing images. The approach employs a dataset from the University of California Irvine (UCI) comprising twenty-one groups of pictures. The images undergo pre-processing, feature extraction using the mentioned DL frameworks, and subsequent categorization through an ensemble classification structure combining Kernel Extreme Learning Machine (KELM) and Support Vector Machine (SVM). The paper concludes with optimal results achieved through performance and comparison analyses.

Fast two-layer nonlinear economic predictive control using machine learning for ORC systems with non-Gaussian disturbances

This study proposes a machine learning-based generalized correntropy two-layer nonlinear economic model predictive control (ML-GC-TL-NEMPC) algorithm to improve the computational speed for Organic Rankine Cycle (ORC) systems with non-Gaussian disturbances. In the upper layer, the ratio of the net output power to the total heat transfer area is used as the economic performance index to optimize the optimal reference trajectory. In the lower layer, the generalized correntropy-based MPC (GC-MPC) is used to track the optimal trajectory. To quickly obtain an optimal solution, a Deep Neural Network (DNN) neural network controller is combined with kernel support vector machine (SVM). It learns the possible optimal solution via off-line training. Then it can be quickly implemented on on-line applications, so it can save the optimal calculation time. The proposed ML-GC-TL-NEMPC is applied to ORC. Its computation and performance are faster and better than the traditional two-layer EMPC and single-layer EMPC.

A single-phase GPU-accelerated surface tension model using SPH

This paper presents an accelerated single-phase surface tension smoothed particle hydrodynamics (SPH) solver developed to run entirely on a graphics processing unit (GPU) capable of simulating millions of particles in three dimensions on a single GPU. The single-phase surface tension model is augmented with a contact line force to improve the prediction of the physics at the liquid-solid contact point. The surface tension model uses the modified dynamic boundary condition (mDBC) to impose no-slip conditions at the wall boundary. To enable simulations with millions of particles, the single-phase surface tension model has been implemented in the open-source SPH code DualSPHysics to exploit the GPU acceleration, paying special attention to the size of the kernel support and integration of the neighbour lists. The new scheme is validated using 2-D and 3-D test cases including drop deformation, drop oscillation, Rayleigh-Plateau instability and surface contact angles. The results show a good agreement with the analytical solutions with a standard spatial convergence behaviour. Profiling the new surface tension solver shows an additional computational complexity. The performance analysis shows that the new code has a speed up of up two orders of magnitude (x70-80) compared to the CPU-only code. Profiling the new CUDA kernels shows they have the near identical performance metrics with the main CUDA kernels in the original DualSPHysics solver.

Ischemic stroke prediction using machine learning in elderly Chinese population: The Rugao Longitudinal Ageing Study.

Compared logistic regression (LR) with machine learning (ML) models, to predict the risk of ischemic stroke in an elderly population in China. We applied 2208 records from the Rugao Longitudinal Ageing Study (RLAS) for ischemic stroke risk prediction assessment. Input variables included 103 phenotypes. For 3-year ischemic stroke risk prediction, we compared the discrimination and calibration of LR model and ML methods, where ML methods include Random Forest (RF), Gaussian kernel Support Vector Machines (SVM), Multilayer perceptron (MLP), K-Nearest Neighbors Algorithm (KNN), and Gradient Boosting Decision Tree (GBDT) to develop an ischemic stroke risk prediction model. Age, pulse, waist circumference, education level, β2-microglobulin, homocysteine, cystatin C, folate, free triiodothyronine, platelet distribution width, QT interval, and QTc interval were significant induced predictors of ischemic stroke. For ischemic stroke prediction, the ML approach was able to tap more biochemical and ECG-related multidimensional phenotypic indicators compared to the LR model, which placed more importance on general demographic indicators. Compared to the LR model, SVM provided the best discrimination and calibration (C-index: 0.79vs. 0.71, 11.27% improvement in model utility), with the best performance in both validation and test data. In a comparison of LR with five ML models, the accuracy of ischemic stroke prediction was higher by combining ML with multiple phenotypes. Combined with other studies based on elderly populations in China, ML techniques, especially SVM, have shown good long-term predictive performance, inspiring the potential value of ML use in clinical practice.

Classification of Alzheimer’s Disease Based on White Matter Connectivity Network

Alzheimer’s disease (AD) is one of the most common irreversible brain diseases in the elderly. Mild cognitive impairment (MCI) is an early symptom of AD, and the early intervention of MCI may slow down the progress of AD. However, due to the subtle neuroimaging differences between MCI and normal control (NC), the clinical diagnosis is subjective and easy to misdiagnose. Machine learning can extract depth features from neural images, and analyze and label them to assist the diagnosis of diseases. This paper combines diffusion tensor imaging (DTI) and support vector machine (SVM) to classify AD, MCI, and NC. First, the white matter connectivity network was constructed based on DTI. Second, the nodes with significant differences between groups were screened out by the two-sample t-test. Third, the optimal feature subset was selected as the classification feature by recursive feature elimination (RFE). Finally, the Gaussian kernel support vector machine was used for classification. The experiment tested and verified the data downloaded from the Alzheimer’s Disease Neuroimaging Initiative (ADNI) database, and the area under the curve (AUC) of AD/MCI and MCI/NC are 0.94 and 0.95, respectively, which have certain competitive advantages compared with other methods.

Entropy Feature Fusion-Based Diagnosis for Railway Point Machines Using Vibration Signals Based on Kernel Principal Component Analysis and Support Vector Machine

Entropy Feature Fusion-Based Diagnosis for Railway Point Machines Using Vibration Signals Based on Kernel Principal Component Analysis and Support Vector Machine

Machine learning classificatory as a tool in the diagnosis of amyotrophic lateral sclerosis using diffusion tensor imaging parameters collected with 1.5T MRI scanner: A case study

The relevance of the study lies in the need to improve the diagnosis of amyotrophic lateral sclerosis (ALS) by utilizing diffusion tensor imaging (DTI) obtained from conventional 1.5 Tesla MRI scanners. The study aimed to investigate the potential of using different machine learning (ML) classifiers to distinguish between individuals with ALS. In this study, five ML classifiers (“support vector machine (SVM)”, “k-nearest neighbors (K-NN)”, naïve Bayesian classifier, “decision tree”, and “decision forest”) were used, based on two DTI parameters: fractional anisotropy and apparent diffusion coefficient, obtained from two manually selected ROIs at the level of the brain pyramids in 47 ALS patients and 55 healthy subjects. The quality of each classifier was evaluated using the confusion matrix and ROC curves. The highest accuracy in differentiating ALS patients from healthy individuals based on DTI data was demonstrated by the radial kernel support vector method (77% accuracy [p=0.01]), while K-NN and “decision tree” classifiers had slightly lower performance, and “decision forest” classifier was overtrained to the training set (AUC=1). The authors have shown a sufficiently accuracy of ML classifier “SVM” in detecting radiological characteristics of ALS in pyramidal tracts.

Recurrence prediction of lung adenocarcinoma using an immune gene expression and clinical data trained and validated support vector machine classifier.

Immune microenvironment plays a critical role in cancer from onset to relapse. Machine learning (ML) algorithm can facilitate the analysis of lab and clinical data to predict lung cancer recurrence. Prompt detection and intervention are crucial for long-term survival in lung cancer relapse. Our study aimed to evaluate the clinical and genomic prognosticators for lung cancer recurrence by comparing the predictive accuracy of four ML models. A total of 41 early-stage lung cancer patients who underwent surgery between June 2007 and October 2014 at New York University Langone Medical Center were included (with recurrence, n=16; without recurrence, n=25). All patients had tumor tissue and buffy coat collected at the time of resection. The CIBERSORT algorithm quantified tumor-infiltrating immune cells (TIICs). Protein-protein interaction (PPI) network and Kyoto Encyclopedia of Genes and Genomes (KEGG) pathway analysis were conducted to unearth potential molecular drivers of tumor progression. The data was split into training (75%) and validation sets (25%). Ensemble linear kernel support vector machine (SVM) ML models were developed using optimized clinical and genomic features to predict tumor recurrence. Activated natural killer (NK) cells, M0 macrophages, and M1 macrophages showed a positive correlation with progression. Conversely, T CD4+ memory resting cells were negatively correlated. In the PPI network, TNF and IL6 emerged as prominent hub genes. Prediction models integrating clinicopathological prognostic factors, tumor gene expression (45 genes), and buffy coat gene expression (47 genes) yielded varying receiver operating characteristic (ROC)-area under the curves (AUCs): 62.7%, 65.4%, and 59.7% in the training set, 58.3%, 83.3%, and 75.0% in the validation set, respectively. Notably, merging gene expression with clinical data in a linear SVM model led to a significant accuracy boost, with an AUC of 92.0% in training and 91.7% in validation. Using ML algorithm, immune gene expression data from tumor tissue and buffy coat may enhance the precision of lung cancer recurrence prediction.

Analyzing Brain Tumor from Structural MR Images Using Kernel Support Vector Machine and Principal Component Analysis

Analyzing Brain Tumor from Structural MR Images Using Kernel Support Vector Machine and Principal Component Analysis

Surface Enhanced Raman Spectroscopy Pb2+ Ion Detection Based on a Gradient Boosting Decision Tree Algorithm

Lead pollution poses a serious threat to the natural environment, and a fast and high-sensitivity method is urgently needed. SERS can be used for the detection of Pb2+ ions, which is urgently needed. Based on the SERS spectral reference data set of lead nitride (Pb(NO3)2), a model for detecting Pb2+ was established by using a traditional machine learning algorithm and the GBDT algorithm. Principal component analysis was used to compare the batch effect reduction in different pretreatment methods in order to find the optimal combination of such methods and machine learning models. The combination of LightGBM algorithms successfully identified Pb2+ from cross-batch data, exceeding the 84.6% balanced accuracy of the baseline correction+ radial basis function kernel support vector machine (BC+RBFSVM) model and showing satisfactory results, with a 91.4% balanced accuracy and a 0.9313 area under the ROC curve.