Support Vector Classifier Model Research Articles

MR-based radiomics predictive modelling of EGFR mutation and HER2 overexpression in metastatic brain adenocarcinoma: a two-centre study

ObjectivesMagnetic resonance (MR)-based radiomics features of brain metastases are utilised to predict epidermal growth factor receptor (EGFR) mutation and human epidermal growth factor receptor 2 (HER2) overexpression in adenocarcinoma, with the aim to identify the most predictive MR sequence.MethodsA retrospective inclusion of 268 individuals with brain metastases from adenocarcinoma across two institutions was conducted. Utilising T1-weighted imaging (T1 contrast-enhanced [T1-CE]) and T2 fluid-attenuated inversion recovery (T2-FLAIR) sequences, 1,409 radiomics features were extracted. These sequences were randomly divided into training and test sets at a 7:3 ratio. The selection of relevant features was done using the least absolute shrinkage selection operator, and the training cohort’s support vector classifier model was employed to generate the predictive model. The performance of the radiomics features was evaluated using a separate test set.ResultsFor contrast-enhanced T1-CE cohorts, the radiomics features based on 19 selected characteristics exhibited excellent discrimination. No significant differences in age, sex, and time to metastasis were observed between the groups with EGFR mutations or HER2 + and those with wild-type EGFR or HER2 (p > 0.05). Radiomics feature analysis for T1-CE revealed an area under the curve (AUC) of 0.98, classification accuracy of 0.93, sensitivity of 0.92, and specificity of 0.93 in the training cohort. In the test set, the AUC was 0.82. The 19 radiomics features for the T2-FLAIR sequence showed AUCs of 0.86 in the training set and 0.70 in the test set.ConclusionsThis study developed a T1-CE signature that could serve as a non-invasive adjunctive tool to determine the presence of EGFR mutations and HER2 + status in adenocarcinoma, aiding in the direction of treatment plans.Clinical relevance statementWe propose radiomics features based on T1-CE brain MR sequences that are both evidence-based and non-invasive. These can be employed to guide clinical treatment planning in patients with brain metastases from adenocarcinoma.

Quantum-Assisted Machine Learning for Enhanced Fraud Detection in Cybersecurity

Innovative methods for information security and fraud prevention are required in today's digital environment due to the expanding volume of data and the increasing complexity of cyber threats. The use of quantum computing techniques to improve fraud detection and classification systems is investigated in this study. The study's machine learning framework integrates three distinct quantum algorithms to improve classification techniques. The first technique uses a Pauli feature map and a Quantum Support Vector Classifier (QSVC) that leverages a quantum kernel to transform classical input into quantum states. The second technique use a ZZ feature map with "linear" entanglement and a support vector classifier model, utilizing quantum kernels to enhance quantum systems. The third method utilizes Variational Quantum Circuits (VQC) with actual amplitudes, which integrate quantum and conventional machine learning techniques to provide optimized classification. The best results were obtained by the QSVC using ZZ feature maps and linear entanglement, which had a precision of 1.0 and a notable decrease in false positives. In order to improve fraud detection systems' accuracy and dependability and offer strong solutions to financial institutions, this study shows how quantum computing has the potential to completely transform cybersecurity.

Resting-state cerebral blood flow and functional connectivity abnormalities in depressed patients with childhood maltreatment: Potential biomarkers of vulnerability?

Childhood maltreatment (CM) is an important risk factor for major depressive disorder (MDD). This study aimed to explore the specific effect of CM on cerebral blood flow (CBF) and brain functional connectivity (FC) in MDD patients. A total of 150 subjects were collected including 55 MDD patients with CM, 34 MDD patients without CM, 19 healthy controls (HC) with CM, and 42 HC without CM. All subjects completed MRI scans and neuropsychological tests. Two-way analysis of covariance was used to detect the main and interactive effects of disease and CM on CBF and FC across subjects. Then, partial correlation analyses were conducted to explore the behavioral significance of altered CBF and FC in MDD patients. Finally, a support vector classifier model was applied to differentiate MDD patients. MDD patients represented increased CBF in bilateral temporal lobe and decreased CBF in right visual cortex. Importantly, significant depression-by-CM interactive effects on CBF were primarily located in the frontoparietal regions, including orbitofrontal cortex (OFC), lateral prefrontal cortex (PFC), and parietal cortex. Moreover, significant FC abnormalities were seen in OFC-PFC and frontoparietal-visual cortex. Notably, the abnormal CBF and FC were significantly associated with behavioral performance. Finally, a combination of altered CBF and FC behaved with a satisfactory classification ability to differentiate MDD patients. These results highlight the importance of frontoparietal and visual cortices for MDD with CM experience, proposing a potential neuroimaging biomarker for MDD identification.

Hindi podcast genre prediction using support vector classifier

AbstractIndia experienced a 23% rise in podcast listening after the Covid‐19 pandemic. The pandemic and screen fatigue led people to seek their favourite old audio podcasts. Podcast genre classification allows listeners to compile a playlist of their favourite tracks; it also helps podcast streaming services provide recommendations to users based on the genre of the podcasts they enjoy. Since the COVID‐19 pandemic, the need for educational content in all forms, including podcasts, has skyrocketed, making it even more crucial to anticipate the genre of educational podcasts. Educational podcasts are a sub‐genre of the broader education genre and typically involve audio recordings of discussions, lectures, or interviews on educational topics. Education podcast genre prediction is required to efficiently classify and arrange educational content and make it simpler for listeners to access and absorb pertinent information. This study focuses on Podcast Genre Prediction, specifically for the Hindi language. In this study, our developed PodGen dataset was used, which consists of 550 five‐minute podcasts with 26,867 sentences, where every podcast was manually annotated into one of the four genre categories (Horror, Motivational, Crime, and Romance). The performance comparison of state‐of‐the‐art machine learning techniques on the PodGen dataset was used to demonstrate accuracy. The best performance on testing data was observed in the Support Vector Classifier model with balanced accuracy: 82.42%, precision (weighted): 83.09%, recall (weighted): 82.42%, and F1 score (weighted): 82.39%.

MP09-07 DEVELOPING AN ARTIFICIAL INTELLIGENCE MODEL TO PREDICT DIFFERENTIAL RENAL FUNCTION USING CONTRAST-ENHANCED CT SCANS

You have accessJournal of UrologyCME1 Apr 2023MP09-07 DEVELOPING AN ARTIFICIAL INTELLIGENCE MODEL TO PREDICT DIFFERENTIAL RENAL FUNCTION USING CONTRAST-ENHANCED CT SCANS Ramon Correa Medero, Daniel Salevitz, Jiwoong Jeong, Bhavik Patel, Imon Banerjee, and Haidar Abdul-Muhsin Ramon Correa MederoRamon Correa Medero More articles by this author , Daniel SalevitzDaniel Salevitz More articles by this author , Jiwoong JeongJiwoong Jeong More articles by this author , Bhavik PatelBhavik Patel More articles by this author , Imon BanerjeeImon Banerjee More articles by this author , and Haidar Abdul-MuhsinHaidar Abdul-Muhsin More articles by this author View All Author Informationhttps://doi.org/10.1097/JU.0000000000003224.07AboutPDF ToolsAdd to favoritesDownload CitationsTrack CitationsPermissionsReprints ShareFacebookLinked InTwitterEmail Abstract INTRODUCTION AND OBJECTIVE: Differential kidney function plays an important role in the management of kidney disorders. We sought to assess if this can be obtained through an automated evaluation of contrast enhanced computed tomography using a combination of deep learning and machine learning algorithms without nuclear medical imaging. METHODS: All patients who underwent kidney nuclear scanning at Mayo Clinic between 2018-2022 were collected. Computerized tomographic (CT) scans of the kidneys that were obtained within a three-month interval before or after the nuclear scans were extracted. Patients who underwent a urological or radiological intervention within this time frame were excluded. A deep learning segmentation model was used to automatically segment kidneys (Figure 1). 2D and 3D radiomics features were extracted and compared between the two kidneys to compute delta radiomics and assess its ability to predict differential kidney function. The performance of these models was reported using receiver operating characteristics, precision, recall, and F1 score. RESULTS: There were 4118 nuclear medical scans. We randomly selected 303 CT scans for review. Following exclusion, there were 203 paired studies (Figure 2). The fine-tuned segmentation model demonstrated a Sorensen-Dice score of 0.7. The best results were obtained when the support vector classifier model was used on 3D delta radiomics features computed from the venous phase of contrast-enhanced CT scans. This model has an AUC of 0.90 with a precision, recall, and F1 score of 0.80, 0.80, and 0.82 respectively, to detect abnormal kidney function. CONCLUSIONS: This proposed automated pipeline can provide important differential kidney function information from contrast-enhanced cross section imaging without the need for dedicated nuclear scans. Source of Funding: None © 2023 by American Urological Association Education and Research, Inc.FiguresReferencesRelatedDetails Volume 209Issue Supplement 4April 2023Page: e106 Advertisement Copyright & Permissions© 2023 by American Urological Association Education and Research, Inc.MetricsAuthor Information Ramon Correa Medero More articles by this author Daniel Salevitz More articles by this author Jiwoong Jeong More articles by this author Bhavik Patel More articles by this author Imon Banerjee More articles by this author Haidar Abdul-Muhsin More articles by this author Expand All Advertisement PDF downloadLoading ...

Maximum Decentral Projection Margin Classifier for High Dimension and Low Sample Size problems

Compared with relatively easy feature creation or generation in data analysis, manual data labeling needs a lot of time and effort in most cases. Even if automated data labeling​ seems to make it better in some cases, the labeling results still need to be checked and verified by manual. The High Dimension and Low Sample Size (HDLSS) data are therefore very common in data mining and machine learning. For classification problems with the HDLSS data, due to data piling and approximate equidistance between any two input points in high-dimension space, some traditional classifiers often give poor predictive performance. In this paper, we propose a Maximum Decentral Projection Margin Classifier (MDPMC) in the framework of a Support Vector Classifier (SVC). In the MDPMC model, the constraints of maximizing the projection distance between decentralized input points and their supporting hyperplane are integrated into the SVC model in addition to maximizing the margin of two supporting hyperplanes. On ten real HDLSS datasets, the experiment results show that the proposed MDPMC approach can deal well with data piling and approximate equidistance problems. Compared with SVC with Linear Kernel (SVC-LK) and Radial Basis Function Kernel (SVC-RBFK), Distance Weighted Discrimination (DWD), weighted DWD (wDWD), Distance-Weighted Support Vector Machine (DWSVM), Population-Guided Large Margin Classifier (PGLMC), and Data Maximum Dispersion Classifier (DMDC), MDPMC obtains better predictive accuracy and lower classification errors than the other seven classifiers on the HDLSS data.

MiR‐9 could mediate the relationship between childhood maltreatment and depression

AbstractBackgroundChildhood maltreatment (CM) is regarded as an important risk factor for major disorder depression (MDD). However, the neural links corresponding to the process of early CM experience producing brain alterations and then leading to depression later remain unclear.PurposeTo explore the neural basis of the effects of CM on MDD and the potential effects of microRNA‐9 (miR‐9) in mediating these processes.MethodForty unmedicated MDD patients and 34 healthy controls (HCs) completed resting‐state fMRI scans and peripheral blood miR‐9 tests. The neural substrates of CM, miR‐9, and depression, as well as their interactive effects on intrinsic amygdala functional connectivity (AFC) network were investigated in MDD patients. Two‐step mediation analysis was separately employed to explore whether AFC strength mediates the association among CM severity, miR‐9 levels, and depression. A support vector classifier (SVC) model of machine learning was used to distinguish MDD patients from HCs.ResultMDD patients showed higher miR‐9 levels that were negatively correlated with CM scores and depressive severity. Overlapping effects of CM, miR‐9, and depressive severity on bilateral AFC networks in MDD patients were primarily located in the prefrontal‐striatum pathway and limbic system. The connection of amygdala to prefrontal‐limbic circuits separately mediated the effects of CM severity on the miR‐9 levels, and the impacts of miR‐9 levels on the severity of depression in MDD patients. Furthermore, the SVC model, which integrated miR‐9 levels, CM severity, and AFC strength in prefrontal‐limbic regions, had good power in differentiating MDD patients from HCs (accuracy 85.1%).ConclusionMiR‐9 may play a crucial role in the process of CM experience‐produced brain changes targeting prefrontal‐limbic regions and that subsequently leads to depression. The present neuroimaging‐epigenetic results provide new insight into our understanding of MDD pathophysiology.

Prediction Breast Cancer as Benign or Malignant in Apache Spark Framework

There are number of diseases that increase the number of deaths over the world. Breast cancer can be considered as the most common of them. Therefore, there is a need to use classification and others data mining methods to study the health datasets in order to diagnosis and make decisions. In this paper, Support Vector Classifier model, Logistic Regression algorithm, and Random Forest algorithm are conducted on the public available Wisconsin Breast Cancer dataset. The experiment is executed in a Scala environment. Moreover, in single and multi-nodes spark cluster. The results show the high accuracy in Support Vector Classifier model and the low error rate in less time consumed when compared with other studies. The authentication in spark are applied in the application by using shared secrete method.

Identification of microRNA-9 linking the effects of childhood maltreatment on depression using amygdala connectivity

Childhood maltreatment (CM) is regarded as an important risk factor for major depressive disorder (MDD). However, the neural links corresponding to the process of early CM experience producing brain alterations and then leading to depression later remain unclear. To explore the neural basis of the effects of CM on MDD and the potential role of microRNA-9 (miR-9) in these processes, we recruited 40 unmedicated MDD patients and 34 healthy controls (HCs) to complete resting-state fMRI scans and peripheral blood miR-9 tests. The neural substrates of CM, miR-9, and depression, as well as their interactive effects on intrinsic amygdala functional connectivity (AFC) networks were investigated in MDD patients. Two-step mediation analysis was separately employed to explore whether AFC strength mediates the association among CM severity, miR-9 levels, and depression. A support vector classifier (SVC) model of machine learning was used to distinguish MDD patients from HCs. MDD patients showed higher miR-9 levels that were negatively correlated with CM scores and depressive severity. Overlapping effects of CM, miR-9, and depressive severity on bilateral AFC networks in MDD patients were primarily located in the prefrontal-striatum pathway and limbic system. The connection of amygdala to prefrontal-limbic circuits could mediate the effects of CM severity on the miR-9 levels, as well as the impacts of miR-9 levels on the severity of depression in MDD patients. Furthermore, the SVC model, which integrated miR-9 levels, CM severity, and AFC strength in prefrontal-limbic regions, had good power in differentiating MDD patients from HCs (accuracy 85.1%). MiR-9 may play a crucial role in the process of CM experience-produced brain changes targeting prefrontal-limbic regions and that subsequently leads to depression. The present neuroimaging-epigenetic results provide new insight into our understanding of MDD pathophysiology.

Optimization of Injection-Molding Process Parameters for Weight Control: Converting Optimization Problem to Classification Problem

Product weight is one of the most important properties for an injection-molded part. The determination of process parameters for obtaining an accurate weight is therefore essential. This study proposed a new optimization strategy for the injection-molding process in which the parameter optimization problem is converted to a weight classification problem. Injection-molded parts are produced under varying parameters and labeled as positive or negative compared with the standard weight, and the weight error of each sample is calculated. A support vector classifier (SVC) method is applied to construct a classification hyperplane in which the weight error is supposed to be zero. A particle swarm optimization (PSO) algorithm contributes to the tuning of the hyperparameters of the SVC model in order to minimize the error between the SVC prediction results and the experimental results. The proposed method is verified to be highly accurate, and its average weight error is 0.0212%. This method only requires a small amount of experiment samples and thus can reduce cost and time. This method has the potential to be widely promoted in the optimization of injection-molding process parameters.

Rockburst prediction in kimberlite with unsupervised learning method and support vector classifier

One of the most serious types of mining disasters in many countries, rockburst leads to injuries, deaths, and damages to facilities, which explains the need to study its prediction. However, due to highly non-linear relationship between the occurrence of rockburst and burst impact factors, traditional mechanism-based prediction methods cannot generate precise results. This paper employed a support vector classifier (SVC) to predict rockburst in kimberlite pipes at a diamond mine. We collected 246 groups of data based on real rockburst cases from all over the world as a supportive database. A novel dimensionality reduction method, t-SNE, helped to reduce relevance of original data attributes, and then, an unsupervised learning method (clustering) was adopted to relabel original data to determine relative intensity of these rockburst cases. After the processed prediction data was fed into the trained SVC model, the prediction results were obtained, which matched real rockburst cases that recently occurred at this mine. This data-driven prediction method can be easily conducted and does not rely on the discussion of rockburst mechanism, which has wide potential applications in rockburst prediction in engineering.

A Feature Set for Structural Characterization of Sphere Gaps and the Breakdown Voltage Prediction by PSO-Optimized Support Vector Classifier

Air insulation strength relates closely to the electrostatic field distribution of the gap configuration. To achieve insulation prediction on the basis of electric field (EF) simulations, the spatial structure is characterized by a feature set including 38 parameters defined on a straight line between sphere electrodes. A support vector classifier (SVC) with particle swarm optimization (PSO) is used to establish a prediction model, whose input variables are those features. The EF nonuniform coefficient f of each sample gap is calculated and used for training sample selection according to the ranges off values. Trained by only 11-sample data, the PSO-optimized SVC model is employed to predict the power frequency breakdown voltages of 260-sphere gaps with a wide range of structure sizes. The predicted values coincide with the standard data given in IEC 60052 very well, with the same trend and minor relative errors. The MAPEs of the five predictions with different training sets are within 2.0%. The model is also effective to predict the breakdown voltages of Φ9.75-cm sphere-Φ6.5-cm sphere gaps, whose MAPEs are within 2.6%. The results demonstrate the effectiveness of the EF feature set and the generalization ability of the SVC model under the case of limited samples. This paper lays the foundation for estimating the dielectric strength of other air gaps with similar structures.

Evaluating quality of tomato during storage using fusion information of computer vision and electronic nose

AbstractA nondestructive method for evaluation of tomato quality was proposed to recognize the different ripening stages of tomatoes and to predict their hardness. Computer vision and electronic nose were used, and data fusion technology was used to establish the decision model of multi‐attribute information fusion. Fisher discriminant analysis (FDA) model and support vector classifier (SVC) model for tomato grading were established. Partial least squares (PLS) model and support vector regression (SVR) model were used for predicting the hardness. Comparing with the single detection technique, the combined system which fused computer vision and electronic nose, achieved better results. In the combined system: with respect to the SVC model, classification accuracy was 96.38% for the training set, 94.20% for the prediction set; while to the FDA model, classification accuracy was 93.48% for the training set, 85.51% for the prediction set; to the PLS model, the correlation coefficient of prediction (Rp) was 94.09% and the root mean square error of prediction (RMSEP) was 2.33 N; to the SVR model, the Rp was 95.14% and RMSEP was 0.03 N. It was observed that more robust and better prediction performance on tomato detection were achieved by using fusion information.Practical applicationsComputer vision, electronic nose, data fusion, and pattern recognition were used for the evaluation of tomato ripeness and hardness. Computer vision captured the color information of tomatoes and electronic nose responded to the smell of tomatoes. After data fusion, information became more abundant and the discrimination models also got better performance. It proved the possibility of nondestructive method for the evaluation of tomatoes quality during storage. So it is feasible to apply this method to detect tomato quality in factory.

Switching impulse discharge voltage prediction of EHV and UHV transmission lines–tower air gaps by a support vector classifier

Discharge voltage prediction of practical air gaps in transmission projects is a long-sought goal and also a great challenge in high-voltage (HV) engineering. An approach combined electric field simulation, feature extraction and machine learning algorithm is presented in this study to predict the switching impulse discharge voltages of extra-HV (EHV) and ultra-HV (UHV) transmission lines-tower air gaps. Some features extracted from the electrostatic field distribution are used to characterise the air-gap configuration and taken as input parameters of a prediction model established by a support vector classifier (SVC). Three kinds of actual gap configurations in EHV and UHV transmission lines are taken as test samples to validate the validity of the SVC model. Trained by experimental data of rod-plane gaps and one of the engineering gap configurations, this model is able to predict the discharge voltages of the other two conductor-tower gaps with acceptable accuracy. The mean absolute percentage errors of the three prediction results are 6.84, 4.19 and 3.46%. This research demonstrates the feasibility of discharge voltage prediction for complicated engineering gaps, which is useful to reduce the costly full-scale tests and helpful to guide the external insulation design.

A study on regularized Weighted Least Square Support Vector Classifier

Least Square Support Vector Machine(LSSVM) has been widely used for solving regression and classification problems due to its simple solution. However, LSSVM has some drawbacks in practice, such as lack of robustness, loss of sparseness of its solution and inapplicability of solving classification problem in some cases. In order to find robust and sparse solution for classification problem by using Least Square methods, we propose a novel regularized Weighted Least Square Support Vector Classifier in this paper. First, we give a basic optimized Weighted Least Square Support Vector Classifier model, which can be used to obtain the best weights according to the distance between samples and classification boundary and obtain an extremely sparse solution. In order to control the sparsity of solution, we further propose a regularized Weighted Least Square Support Vector Classifier model. After theoretical analysis of regularization function, we construct 2 kinds of regularization functions which meet our requirements and then design relative algorithms for optimizing weights and finding the best solution. The proposed method is evaluated on artificial datasets and several important benchmark databases in Machine Learning, and achieves the more encouraging results compared with some state-of-the-art approaches.

Fault Diagnosis of Steam Turbine-Generator Sets Using an EPSO-Based Support Vector Classifier

This paper proposes an enhanced particle swarm optimization (EPSO)-based support vector classifier (SVC) that extracts the support vector from databases, in order to diagnose vibration faults in steam turbine-generator sets (STGS). SVC has been successfully applied to the classification of data with linear or nonlinear features, because it allows generalization. However, the design of the best SVC model for the acquisition of the best hyperplane is often difficult and depends heavily on the operators' experience or on trial-and-error experiments. In this paper, an EPSO algorithm is used to automatically tune the control parameters of an SVC. Since EPSO is an excellent optimization tool, it is easily sufficient for the design of an optimal SVC model. The proposed approach is applied to an STGS, to test its diagnostic accuracy. The test results demonstrate that the proposed EPSO-based SVC method has a higher diagnostic accuracy and a shorter learning time than classical neural network-based methods. This study also provides advice on handling a loss of data features for unknown reasons.

Apnea MedAssist: Real-time Sleep Apnea Monitor Using Single-Lead ECG

We have developed a low-cost, real-time sleep apnea monitoring system ''Apnea MedAssist" for recognizing obstructive sleep apnea episodes with a high degree of accuracy for both home and clinical care applications. The fully automated system uses patient's single channel nocturnal ECG to extract feature sets, and uses the support vector classifier (SVC) to detect apnea episodes. "Apnea MedAssist" is implemented on Android operating system (OS) based smartphones, uses either the general adult subject-independent SVC model or subject-dependent SVC model, and achieves a classification F-measure of 90% and a sensitivity of 96% for the subject-independent SVC. The real-time capability comes from the use of 1-min segments of ECG epochs for feature extraction and classification. The reduced complexity of "Apnea MedAssist" comes from efficient optimization of the ECG processing, and use of techniques to reduce SVC model complexity by reducing the dimension of feature set from ECG and ECG-derived respiration signals and by reducing the number of support vectors.