Support Vector Machine Research Articles

Spatiotemporal trends and drivers of forest cover change in Metekel Zone forest areas, Northwest Ethiopia.

The spatiotemporal dynamics of forest cover are essential for understanding the patterns and processes of forest change over time and space. This research focused on the spatiotemporal trends and drivers of forest cover change in the Metekel Zone of Northwest Ethiopia. Landsat 5, Landsat 7, and Landsat 8 imagery, covering the period from 1986 to 2019, were used for land use/cover classification. Land use/cover classification was performed using random forest (RF) and support vector machine (SVM) algorithms in the Google Earth Engine (GEE) platform, with training samples obtained through visual image interpretation. Spectral indices, such as the normalized difference vegetation index, soil-adjusted vegetation index, leaf area index, and normalized difference water index, were analyzed to examine forest cover dynamics over time. In addition, key informant interviews (KIIs) and focus group discussions (FGDs) were conducted. Findings revealed that forest cover decreased significantly from 51.37% in 1986 to 17.20% in 2019, driven largely by human activities such as agricultural expansion, increased demand for firewood, and urban expansion. Findings from spectral indices further corroborated the finding that forest cover in the study region (mainly in the southwestern part) substantially decreased from 1986 to 2019. Concerning forest depletion, the lack of local community awareness has become a key challenge. This problem is attributed to communities prioritizing immediate needs such as fuel and land for agriculture over long-term forest conservation. To combat ongoing deforestation, the Metekel Zone Administration, in collaboration with the land administration office and other stakeholders, revisited and strengthened existing forest policies and control systems. It is also suggested that community awareness, chiefly among youth, should be enhanced through the strategic expansion of formal and nonformal educational initiatives, which empower the youth as agents of change and promote the dissemination of knowledge throughout the community.

Advanced Mineral Deposit Mapping via Deep Learning and SVM Integration With Remote Sensing Imaging Data

ABSTRACTAutomating mineral delineation and rock type analysis using remote sensing imaging data is a critical application of machine learning. Traditional machine learning methods often struggle with accuracy and precise map generation. This study aims to enhance performance through a refined deep learning model. In this work, we present a deep learning pipeline to map the mineral deposits in the study area. Initially, we apply a deep convolutional neural network (CNN) to a specialized mineral dataset to map mineral deposits within the study area. Subsequently, we build a hybrid model combining deep CNN layers with a support vector machine (SVM). This merger significantly improves classification accuracy from an initial 92.7% to 95.3%. In our approach, CNN layers function as feature extractors while the SVM serves as the classification model. Moreover, we conduct an evaluation of the SVM using polynomial kernels of degrees 3, 6, 9, and 12. The results indicate that the SVM with a degree of 12 achieved the highest classification accuracy, followed by degrees 9, 6, and 3. Experimental results demonstrate the effectiveness of our proposed method for classifying remote sensing imaging data, showcasing its potential for advancing mineral delineation and rock type analysis.

Reliable Augmentation and Precise Identification of EPG Waveforms Based on Multi-Criteria DCGAN

The electrical penetration graph (EPG) technique is of great significance in elucidating the mechanisms of virus transmission by piercing-sucking insects and crop resistance to these insects. The traditional method of manually processing EPG signals encounters the drawbacks of inefficiency and subjectivity. This study investigated the data augmentation and automatic identification of various EPG signals, including A, B, C, PD, E1, E2, and G, which correspond to distinct behaviors exhibited by the Asian citrus psyllid. Specifically, a data augmentation method based on an improved deep convolutional generative adversarial network (DCGAN) was proposed to address the challenge of insufficient E1 waveforms. A multi-criteria evaluation framework was constructed, leveraging maximum mean discrepancy (MMD) to evaluate the similarity between the generated and real data, and singular value decomposition (SVD) was incorporated to optimize the training iterations of DCGAN and ensure data diversity. Four models, convolutional neural network (CNN), K-nearest neighbors (KNN), decision tree (DT), and support vector machine (SVM), were established based on DCGAN to classify the EPG waveforms. The results showed that the parameter-optimized DCGAN strategy significantly improved the model accuracies by 5.8%, 6.9%, 7.1%, and 7.9% for DT, SVM, KNN, and CNN, respectively. Notably, DCGAN-CNN effectively addressed the skewed distribution of EPG waveforms, achieving an optimal classification accuracy of 94.13%. The multi-criteria optimized DCGAN-CNN model proposed in this study enables reliable augmentation and precise automatic identification of EPG waveforms, holding significant practical implications for understanding psyllid behavior and controlling citrus huanglongbing.

Assessing groundwater quality in the northwestern coastal area of Sri Lanka using multivariate statistical techniques

The objective of the present study was to assess groundwater quality in the northwestern coastal region of Sri Lanka by analyzing hydrogeochemical data using multivariate techniques. The study examined the relationship between water quality and sources influencing groundwater quality and proposed useful statistical tools for water resource management. Descriptive, comparative, correlation, factor analysis (FA), and discriminant analysis (DA) were among the techniques used. The water quality in terms of electrical conductivity (EC), total dissolved solids (TDS), and dissolved nitrate and phosphate concentrations of the northwestern coastal area, where different aquifer conditions prevailed, were compared, and differences in the mean concentrations of the above parameters were identified. The study also employed ridge regression and support vector machines (SVM) to predict nitrate levels and validate the results using a 70:30 train/test split. The analysis found that the mean concentrations of EC, TDS, and HCO3- are higher in the sandy aquifer area, while Fe2+ and PO43- are higher in the regolith aquifer area. EC, TDS, PO43-, and HCO3- in the hard-rock aquifer area exceed permissible limits. Factor analysis identified four factors contributing to pollution, and a linear discriminant model classified all observations with 99.9% accuracy. The water quality index for Kalpitiya, Vanathavillu, and Katana-Negombo areas was 68.1, 99.2, and 287.9, respectively, while the World Health Organization (WHO) cutoff was 50. The use of multivariate statistical techniques demonstrated the value of analyzing hydrogeochemical data to gain valuable insights into the complex interplay of factors affecting groundwater quality. The SVM model, using a linear kernel, was identified as the best model to predict nitrate levels. A combination of statistical analyses reveals that, with the exclusion of a few wells, the groundwater in the study area is polluted and inappropriate for human consumption or culinary purposes. Nonetheless, the inhabitants persist in utilizing it as their primary source of drinking water. This study reveals the combination of statistical analyses is useful for the management of groundwater resources.

Machine Learning Based Decision Support System for the Diagnosis of Breast Cancer

Breast cancer is among the most prevalent diseases encountered among women worldwide. Early diagnosis of breast cancer is crucial for the treatment of the disease. Detecting the disease at an early stage prevents deaths resulting from the condition. Recently, computer-aided systems have been developed to ensure early-stage diagnosis and accuracy of breast cancer. Computer-aided systems developed with machine learning approaches significantly contribute to the process of diagnosing breast cancer. The aim of this study is to propose a new classification system based on machine learning algorithms developed for the diagnosis of breast cancer. In this study, sub-data sets were created by reducing features, and data cleaning processes were applied. After these procedures, stages such as feature selection and feature extraction were applied. In this study, classification processes such as Ensemble, k- Nearest Neighbors (kNN), Support Vector Machines (SVMs), and Hybrid Artificial Intelligence were used in line with machine learning. With the obtained results, a Breast Cancer diagnosis algorithm was created. Performance evaluation criteria such as accuracy rate, specificity, sensitivity, kappa number and F-Measure were applied to the created algorithms. In the results obtained in this study, the highest accuracy rate was found to be 99.3% with the Ensemble method, the highest specificity rate was 98.7% with the Ensemble method, and the highest sensitivity rate was found to be 100% with many methods. In light of these results, it was observed that the machine learning algorithms used in this study, implemented in the Matlab environment, were effective. Consequently, it was proven that higher accuracy, specificity, and sensitivity rates can be found with different machine learning techniques. This also demonstrates that the study in our article is a reliable one in detecting diseased and healthy individuals in the diagnosis of breast cancer, showing that it is a more applicable and feasible study in the healthcare field.

Machine learning driven design of high-performance Al alloys

Aluminum (Al) alloys with both high strength and thermal conductivity (TC) are promising structural materials for wide application across different industries. Yet, design of such alloys is challenging, since strength and TC often share a trade-off. In this paper, we build prediction models for TC and ultimate tensile strength (UTS) of Al alloys using eXtreme gradient boosting (XGBoost) and support vector machine (SVM) algorithms, respectively. The models take physical descriptors from the alloy composition into account. Lasso and Gini Impurity algorithms were adopted for feature engineering. Guided by the models, an Al-2.64Si-0.43Mg-0.10Zn-0.03Cu alloy with TC over 190 W·m-1·K-1 and UTS over 220 MPa was designed. The alloy was fabricated and tested by experiment, and its UTS and TC are close to the model prediction. Microstructure characterization suggests that the fragmented and spherical Si phase, along with a few non-spherical Si phases, may be a key reason for the improved properties.

How Can Machine Learning Contribute to the Credit Scoring Process in SME Lending?

This research investigates the potential of machine learning to enhance the credit scoring process in small and medium-sized enterprise (SME) lending. SMEs are vital to global economies, accounting for over 90\% of businesses and more than half of total employment worldwide, according to The World Bank (2023). In emerging economies, SME lending is particularly crucial, providing access to capital that supports economic growth and development. However, assessing the credit risk of SMEs poses unique challenges due to limited financial histories and variable cash flows, making accurate credit scoring essential for lenders. Machine learning offers promising solutions for the risk assessment process in SME lending, leveraging algorithms and large datasets to identify patterns and improve decision-making. By applying techniques such as artificial neural networks, decision tree learning, gradient boosting, logistic regression, random forest, and support vector machines, machine learning can enhance the accuracy and efficiency of credit scoring models. This research explores how these machine learning methods can reduce biases, improve risk prediction, and ultimately support sustainable lending practices by enabling lenders to make more informed credit decisions. The findings aim to illustrate the transformative potential of machine learning in SME credit scoring, offering a framework for financial institutions seeking to integrate advanced data-driven technologies in the credit assessment process.

Machine learning-based clustering analysis of the banking green credit for the renewable energy industry

Credit policies for clean and renewable energy businesses play a crucial role in supporting carbon neutrality efforts to combat climate change. Clustering the credit capacity of these companies to prioritize lending is essential given the limited capital available. Support Vector Machine (SVM) and Artificial Neural Network (ANN) are two robust machine learning algorithms for addressing complex clustering problems. Additionally, hyperparameter selection within these models is effectively enhanced through the support of a robust heuristic optimization algorithm, Particle Swarm Optimization (PSO). To leverage the strength of these advanced machine learning techniques, this paper aims to develop SVM and ANN models, optimized with the PSO, for the clustering problem of green credit capacity in the renewable energy industry. The results show low Mean Square Error (MSE) values for both models, indicating high clustering accuracy. The credit capabilities of wind energy, clean fuel, and biomass pellet companies are illustrated in quadrant charts, providing stakeholders with a clear view to adjust their credit strategies. This helps ensure the efficient operation of banking green credit policies.

Thermal Runaway Warning of Lithium Battery Based on Electronic Nose and Machine Learning Algorithms

Characteristic gas detection can be an efficient way to predict the degree of thermal runaway of a lithium battery. In this work, a sensor array consisting of three commercial MOS sensors was employed to discriminate between three target gases, CO, H2 and a mixture of the two, which are characteristic gases released during the thermal runaway of lithium batteries. In this work, an integrated model that makes the classification stage results one of the feature inputs for the concentration regression stage was employed, successfully reducing the RMSE of the concentration regression results. In addition, we also explored the influence of the selection of the response time length on the classification and regression tasks, achieving the best results in a short time through the optimum algorithm. To assess the impact of time duration sensor data on the results, we selected four time windows of different length and extracted the corresponding sensor response data for subsequent processing. Initially, principal component analysis (PCA) was used to visualise the clustering of the three target gas samples at room temperature, providing a preliminary data analysis. For the classification phase, we chose three classification algorithms—MLP (Multilayer Perceptron), ELM (Extreme Learning Machine), and SVM (Support Vector Machine)—and performed a comprehensive comparison of their classification and generalisation abilities using grid search for hyperparameter optimisation and five-fold cross-validation. The results demonstrated that MLP achieved 99.23% classification accuracy during the 20 s response period. In the concentration regression phase, we combined the classification results with the raw features to create a new feature set, which was then input into a multi-output MLP regression model. The root mean square error (RMSE) employing the new feature set was used to measure the prediction error. Ultimately, the findings showed that the input of combined features significantly reduced the regression error for the mixed gas.

Interpretable prediction of 30-day mortality in patients with acute pancreatitis based on machine learning and SHAP.

Severe acute pancreatitis (SAP) can be fatal if left unrecognized and untreated. The purpose was to develop a machine learning (ML) model for predicting the 30-day all-cause mortality risk in SAP patients and to explain the most important predictors. This research utilized six ML methods, including logistic regression (LR), k-nearest neighbors(KNN), support vector machines (SVM), naive Bayes (NB), random forests(RF), and extreme gradient boosting(XGBoost), to construct six predictive models for SAP. An extensive evaluation was conducted to determine the most effective model and then the Shapley Additive exPlanations (SHAP) method was applied to visualize key variables. Utilizing the optimized model, stratified predictions were made for patients with SAP. Further, the study employed multivariable Cox regression analysis and Kaplan-Meier survival curves, along with subgroup analysis, to explore the relationship between the machine learning-based score and 30-day mortality. Through LASSO regression and recursive feature elimination (RFE), 25 optimal feature variables are selected. The XGBoost model performed best, with an area under the curve (AUC) of 0.881, a sensitivity of 0.5714, a specificity of 0.9651 and an F1 score of 0.64. The first six most important feature variables were the use of vasopressor, high Charlson comorbidity index, low blood oxygen saturation, history of malignant tumor, hyperglycemia and high APSIII score. Based on the optimal threshold of 0.62, patients were divided into high and low-risk groups, and the 30-day survival rate in the high-risk group decreased significantly. COX regression analysis further confirmed the positive correlation between high-risk scores and 30-day mortality. In the subgroup analysis, the model showed good risk stratification ability in patients with different gender, renal replacement therapy and with or without a history of malignant tumor, but it was not effective in predicting peripheral vascular disease. the XGBoost model effectively predicts the severity of SAP, serving as a valuable tool for clinicians to identify SAP early.

Applying a Support Vector Machine (SVM-RFE) Learning Approach to Investigate Students’ Scientific Literacy Development: Evidence from Asia, Europe, and South America

Cultivating scientific literacy is a goal widely shared by educators and students around the world. Many studies have sought to enhance students’ proficiency in scientific literacy through various approaches. However, there is a need to explore the attributes associated with advanced levels of scientific literacy, especially the influence of contextual factors. In this context, our study employs a machine learning technique—the SVM-RFE algorithm—to identify the critical characteristics of students with strong scientific literacy in Asia, Europe, and South America. Our research has pinpointed 30 key factors from a broader set of 162 contextual factors that are indicative of outstanding scientific literacy among 15-year-old secondary school students. By utilizing student samples from the three continents, our study provides a comprehensive analysis of these factors across the entire dataset, along with a comparative examination of the optimal set of key factors between continents. The findings highlight the importance of these key factors, which should be considered by educational policymakers and school leaders when developing educational policies and instructional strategies to foster the most effective development of scientific literacy.

Evaluating Feature Impact Prior to Phylogenetic Analysis Using Machine Learning Techniques

The purpose of this paper is to describe a feature selection algorithm and its application to enhance the accuracy of the reconstruction of phylogenetic trees by improving the efficiency of tree construction. Applying machine learning models for Arabic and Aramaic scripts, such as deep neural networks (DNNs), support vector machines (SVMs), and random forests (RFs), each model was used to compare the phylogenies. The methodology was applied to a dataset containing Arabic and Aramaic scripts, demonstrating its relevance in a range of phylogenetic analyses. The results emphasize that feature selection by DNNs, their essential role, outperforms other models in terms of area under the curve (AUC) and equal error rate (EER) across various datasets and fold sizes. Furthermore, both SVM and RF models are valuable for understanding the strengths and limitations of these approaches in the context of phylogenetic analysis This method not only simplifies the tree structures but also enhances their Consistency Index values. Therefore, they offer a robust framework for evolutionary studies. The findings highlight the application of machine learning in phylogenetics, suggesting a path toward accurate and efficient evolutionary analyses and enabling a deeper understanding of evolutionary relationships.

SFMD‐X: A New Functional Data Classifier Based on Shrinkage Functional Mahalanobis Distance

ABSTRACTIn this article, we propose a novel classification approach for functional data based on a shrinkage estimate of functional Mahalanobis distance. We first introduce a new shrinkage functional Mahalanobis distance (SFMD), by using this new distance, we transform the functional observations into a set of vector‐valued pseudo‐samples. Furthermore, we adopt some good classification algorithms designed for multivariate data to this pseudo‐samples instead of the original functional data. The new approach has advantage of highly flexible and scalable, that is, it can easily combine with any classification algorithm, such as support vector machine, tree‐based methods, and neural networks. We demonstrate the performance of the proposed functional classifier through both extensive simulation studies and two real data applications.

Enhancing Forest Canopy Height Mapping in Kaziranga National Park, Assam, by Integrating LISS IV and SAR data with GEDI LiDAR data Using Machine Learning

Abstract. This study investigates the integration of spaceborne Global Ecosystem Dynamics Investigation (GEDI) LiDAR data with optical imagery from Linear Imaging Self Scanning Sensor (LISS IV), Sentinel-1 Synthetic Aperture Radar (SAR) and PALSAR data for continuous forest canopy height mapping in Kaziranga National Park (KNP), Assam for the years 2018 and 2022. Four machine learning models were trained and evaluated to assess the predictive ability of LISS IV data in conjunction with SAR variables. The mean canopy height was measured at approximately 8.58 m in 2018, which increased to about 9.07m in 2022. Results reveal Extreme Gradient Boosting (XGB) as the top-performing model, achieving an RMSE of 5.47m and an R2 of 0.55. In comparison, Random Forest (RF), Support Vector Machine (SVM), and k-Nearest Neighbors (kNN) achieved RMSE values of 5.49, 5.51, and 5.73, respectively. Analysis shows a prevalent occurrence of canopy heights below 5 meters in KNP (more than 35% of the area), while taller canopies beyond 20m can be found in less than 5% of the area. This finding underscores the importance of integrating satellite data and machine learning and highlights the novel application of LISS IV data in enhancing canopy height mapping. Furthermore, it represents the first comprehensive attempt to map canopy height in KNP, laying the groundwork for further research on biomass assessment and carbon sequestration in this vital biodiversity hotspot. Overall, the study highlights the potential of leveraging advanced remote sensing technologies and machine learning approaches for improved understanding and management of forest ecosystems.

Measurement of sulfur content in coal mining areas by using field-remote sensing data and an integrated deep learning model

High-quality coal emits a smaller amount of harmful substances during the combustion process, which greatly reduces the environmental hazard. The sulfur content of coal is one of the important indicators that determine coal quality. The world’s demand for high-quality coal is increasing. This is challenging for the coal mining industry. Therefore, how to quickly determine the sulfur content of coal in coal mining areas has always been a research difficulty. This study is the first to map the distribution of sulfur content in opencast coal mines using field-remote sensing data, and propose a novel method for evaluating coal mine composition. We collected remote sensing, field visible and near-infrared (Vis-NIR) spectroscopy data and built analytical models based on a tiny neural network based on the convolutional neural network. The experimental results show that the proposed method can effectively analyze the coal sulfur content. The coal recognition accuracy is 99.65%, the root-mean-square error is 0.073 and the R is 0.87, and is better than support vector machines and partial least squares methods. Compared with traditional methods, the proposed method shows many advantages and superior performance.

Spatiotemporal land use land cover (LULC) change analysis of urban narrow river using Google Earth Engine and Machine learning algorithms in Monterrey, Mexico

Abstract. This study evaluates four Machine Learning Algorithms—Random Forest (RF), K-Means Clustering, Support Vector Machine (SVM), and Classification and Regression Trees (CART)—for precise land use and land cover (LULC) classification in the Monterrey Metropolitan Area. During the period 2016-2019, and with alternating wet and dry season classifications, the research addresses challenges in identifying narrow rivers, using geospatial tools and it does notably the Pesqueria River, which is specially the most narrow and shallow river in the area. Five classes—Water, Vegetation, Urban, and Soil—were classified, achieving precision rates above 85%. Remarkably, SVM exhibited an excellent accuracy, particularly for narrow rivers, showcasing its utility in complex urban landscapes. The study utilizes high resolution satellite imagery with a spatial resolution of 4.7m, contributing to the reliability of the results. Emphasizing temporal dynamics, the research links LULC changes to urbanization, infrastructure, and seasonal variations, offering vital insights for sustainable urban development.

Enhancing SARS-CoV-2 Lineage Surveillance through the Integration of a Simple and Direct qPCR-Based Protocol Adaptation with Established Machine Learning Algorithms.

Emerging and evolving Severe Acute Respiratory Syndrome Coronavirus 2 (SARS-CoV-2) lineages, adapted to changing epidemiological conditions, present unprecedented challenges to global public health systems. Here, we introduce an adapted analytical approach that complements genomic sequencing, applying a cost-effective quantitative polymerase chain reaction (qPCR)-based assay. Viral RNA samples from SARS-CoV-2 positive cases detected by diagnostic laboratories or public health network units in Ceará, Brazil, were tracked for genomic surveillance and analyzed by using paired-end sequencing combined with integrative genomic analysis. Validation of a key structural variation was conducted with gel electrophoresis for the presence of a specific open reading frame 7a(ORF7a) gene deletion within the "BE.9" lineages tracked. The analytical innovation of our method is the optimization of a simple intercalating dye-based qPCR assay through repositioning primers from the ARTIC v4.1 amplicon panel to detect large molecular patterns. This assay distinguishes between "BE.9" and "non-BE.9" lineages, particularly BQ.1, without the need for expensive probes or sequencing. The protocol was validated against lineage predictions from next-generation sequencing (NGS) using 525 paired samples, achieving 93.3% sensitivity, 95.1% specificity, and 92.4% agreement, as measured by Cohen's Kappa coefficient. Machine learning (ML) models were trained using the melting curves from intercalating dye-based qPCR of 1724 samples, enabling highly accurate lineage assignment. Among them, the support vector machine (SVM) model had the best performance and after fine-tuning showed ∼96.52% (333/345) accuracy in comparison to the test data set. Our integrated approach provides an adapted analytical method that is both cost-effective and scalable, suitable for rapid assessment of emerging variants, especially in resource-limited settings. In this work, the protocol is applied to improve the monitoring of SARS-CoV-2 sublineages but can be extended to track any key molecular signature, including large insertions and deletions (indels) commonly observed in pathogenic agent subtypes. By offering a complement to traditional sequencing methods and utilizing easily trainable machine learning algorithms, our methodology contributes to enhanced molecular surveillance strategies and supports global efforts in pandemic control.

An Assist-as-Needed Control Strategy Based on a Subjective Intention Decline Model

In the rehabilitation training process for stroke patients, the level of excitement in the patient’s physiological state has a positive impact on the efficacy of the training. In order to improve patients’ initiative during training and prevent dependence on assistive systems, this study proposes an assist-as-needed control strategy based on a subjective intention decline model. The strategy primarily consists of two modules: a subjective intention decline control module and a limb movement assessment module. The subjective intention decline module collects surface electromyography (sEMG) data during patient training and optimizes support vector machine (SVM) using quantum particle swarm optimization (QPSO) algorithms to establish a subjective intention decline model. The limb movement assessment module collects information such as interaction force and position error during training and proposes a method for evaluating the motion state of the affected limb. This model combines traditional impedance control with a method for assessing limb movement and subjective status, automatically adjusting the level of assistive force on the affected limb in real time to enhance its active participation in tasks. Finally, we performed two verification experiments to assess the patient’s initiative in participating in the training. The experimental results show that the proposed method effectively reduced the average assist force by 65.66% for the traditional impedance control training system and effectively the average assist force by 35.2% for the control training system using only the assist force module based on force position information. At the same time, the accuracy of the subjective intention attenuation module established in the experiment to identify the fatigue level of the subjects reached 93.41%. Therefore, the proposed method effectively improves the initiative of trainers and also prevents patients from relying on the assist-as-needed control training system.

Optimizing SVM for argan tree classification using Sentinel-2 data: A case study in the Sous-Massa Region, Morocco

The development of efficient classifiers for land cover remains challenging due to the presence of hyperparameters in the model. Conventional approaches rely on manual tuning, which is both time-consuming and impractical, often leading to suboptimal results. This study aimed to optimize the hyperparameters of the Support Vector Machine (SVM) algorithm using the grid search method to map the distribution of the Argan forest in the Souss-Massa region of Morocco from Sentinel-2 satellite image. To achieve this, we examined the C parameter for the linear function, as well as the C and gamma parameters for the radial RBF and sigmoid functions. Similarly, we explored the C, gamma, and degree parameters for the polynomial function chosen using the grid search method. These parameters are compared with the default hyperparameters of each SVM function. The results are validated using the cross-validation method and by the following scores: accuracy, precision, recall, F1 score, and Cohen’s Kappa. The experiments were conducted using the Earth Engine Python API in Google Colab (Google Collaboratory). In addition, experimental results indicate that the hyperparameters selected by grid search yield higher scores than the default hyperparameters. The best results were achieved using the hyperparameters of the polynomial base kernel, specifically with C = 10, degree = 2, and gamma = 10. Accuracy = 96.61%.

Identification of a Novel Biomarker Panel for Breast Cancer Screening

Breast cancer remains a major public health concern, and early detection is crucial for improving survival rates. Metabolomics offers the potential to develop non-invasive screening and diagnostic tools based on metabolic biomarkers. However, the inherent complexity of metabolomic datasets and the high dimensionality of biomarkers complicates the identification of diagnostically relevant features, with multiple studies demonstrating limited consensus on the specific metabolites involved. Unlike previous studies that rely on singular feature selection techniques such as Partial Least Square (PLS) or LASSO regression, this research combines supervised and unsupervised machine learning methods with random sampling strategies, offering a more robust and interpretable approach to feature selection. This study aimed to identify a parsimonious and robust set of biomarkers for breast cancer diagnosis using metabolomics data. Plasma samples from 185 breast cancer patients and 53 controls (from the Cooperative Human Tissue Network, USA) were analyzed. This study also overcomes the common issue of dataset imbalance by using propensity score matching (PSM), which ensures reliable comparisons between cancer and control groups. We employed Univariate Naïve Bayes, L2-regularized Support Vector Classifier (SVC), Principal Component Analysis (PCA), and feature engineering techniques to refine and select the most informative features. Our best-performing feature set comprised 11 biomarkers, including 9 metabolites (SM(OH) C22:2, SM C18:0, C0, C3OH, C14:2OH, C16:2OH, LysoPC a C18:1, PC aa C36:0 and Asparagine), a metabolite ratio (Kynurenine-to-Tryptophan), and 1 demographic variable (Age), achieving an area under the ROC curve (AUC) of 98%. These results demonstrate the potential for a robust, cost-effective, and non-invasive breast cancer screening and diagnostic tool, offering significant clinical value for early detection and personalized patient management.