Support Vector Machine Approach Research Articles

An ensemble-based approach for effective distributed denial of service attack detection in software defined networking

<p>Software defined networking (SDN) is a network framework that aims to redefine network characteristics through the programmability of network components, faster and larger network monitoring, centralized network operation, and effective detection of fraudulent traffic and special malfunctions. However, SDN networks are vulnerable to security threats that can cause complete network failure. To address this issue, in this paper, machine learning techniques are suggested for the swift detection of attacks. Various methods for detecting distributed denial of service (DDoS) attacks are evaluated, and the study identifies the most precise method for categorizing such attacks within a SDN network. The results indicate that the proposed system achieves high accuracy in detecting DDoS attacks, with ensemble learning achieving 99% accuracy. This indicates a remarkable improvement percentage in comparison to the approaches of decision tree (DT), k-nearest neighbors (KNN), and support vector machine (SVM).</p>

Prediction of shear stress distribution in compound channel with smooth converging floodplains

Abstract Climate change can have a profound impact on river flooding, leading to increased frequency and severity of floods. To mitigate these effects, it is crucial to focus on enhancing early warning systems and bolstering infrastructure resilience through improved forecasting. This proactive approach enables communities to better plan for and respond to flood events, thereby minimizing the adverse consequences of climate change on river floods. During river flooding, the channels often take on a compound nature, with varying geometries along the flow length. This complexity arises from construction and agricultural activities along the floodplains, resulting in converging, diverging, or skewed compound channels. Modelling the flow in these channels requires consideration of additional momentum transfer factors. In this study, machine learning techniques, including Gene Expression Programming (GEP), Artificial Neural Networks (ANN), and Support Vector Machines (SVM), were employed. The focus was on a compound channel with converging floodplains, predicting the shear force carried by the floodplains in terms of non-dimensional flow and hydraulic parameters. The findings indicate that the proposed ANN model outperformed GEP, SVM, and other established approaches in accurately predicting floodplain shear force. This research underscores the efficacy of utilizing machine learning techniques in the examination of river hydraulics.

Predicting hourly heating load in residential buildings using a hybrid SSA–CNN–SVM approach

This study proposes a hybrid prediction model using sparrow search algorithm (SSA) to optimize the convolutional neural network (CNN) and support vector machine (SVM), in order to perform accurate prediction of secondary supply temperature (Ts2). The historical operation data of Weifang residential building thermal station was adopted and reasonable data preprocessing was performed to suppress the interference of abnormal data. The input variables of the prediction model were screened using the correlation analysis method, taking the influence of the hysteresis effect into consideration. The SSA–CNN–SVM model was then developed for prediction. The performance of the model was evaluated by the root mean square error, mean absolute error, mean absolute percentage error (MAPE), and absolute value of relative error of each time step. The results obtained demonstrated that the SSA–CNN–SVM model has high prediction accuracy. The MAPE values of the two heat exchange stations were between 2.28 % and 2.4 %. The indoor temperature significantly affected the prediction accuracy of Ts2. After the introduction of the indoor temperature, the MAPE of the predicted values of the hybrid model was reduced by 0.35 %. The maximum reduction in MAPE of the SSA–CNN–SVM model was 1.5 % compared with other prediction models.

Muscle fatigue detection based on sEMG signal using autocorrelation function and neural networks

Abstract Feature extraction from an recorded surface electromyography (sEMG) signal plays an important role in identifying and quantifying the characteristics of muscle activities. These features can be used for various applications like muscle function assessment, muscle fatigue detection, etc. Common features extracted from sEMG signal are time-domain or frequency-domain features. However, features which are sensitive to uncertainties in the signal like noise, movement artifacts, and outliers should be avoided. Autocorrelation function (ACF), which is a measure of similarity between a signal and its time delayed version, is considered in this work as a feature to overcome the impact of noise, artifacts, and outliers. An artificial neural network (ANN) is developed to differentiate between fatigue and non-fatigue conditions using the calculated ACF from sEMG segments. The performance of an ANN model that can be adapted by means of various regularization methods was investigated. The proposed ANN model achieved an accuracy of about 97.62 %, a precision of about 95.50 % and a sensitivity of about 100 % in the classification of fatigue and non-fatigue sEMG segments, outperforming k-means and linear support vector machine approaches that served as references.

Enhancing Student Performance Prediction Using a Combined SVM-Radial Basis Function Approach

This research aims to improve student performance predictions using a combined SVM (Support Vector Machine) and radial basis function (RBF) approach. The developed model utilizes a combination of the strengths of SVM in handling class separation and the ability of RBF to capture complex patterns in data. Student assessment data, including math, reading, and writing scores, is used as a feature to predict student performance on tests. Preprocessing steps, including feature normalization and label encoding, are applied to prepare the data for model training. Next, the SVM model with the RBF kernel is initialized and optimized using GridSearchCV to find the best parameters. Model evaluation was carried out using the R2 metric to evaluate how well the model predicts student performance. Experimental results show that the combined SVM-RBF approach can improve student performance predictions with fairly accurate prediction results of 88%. The practical implication of this research is the development of a more accurate model for predicting student performance, which can be used as a tool to improve educational interventions and decision-making in educational institutions.

Multimodality quantitative ultrasound envelope statistics imaging based support vector machines for characterizing tissue scatterer distribution patterns: Methods and application in detecting microwave-induced thermal lesions

Ultrasound envelope statistics imaging, including ultrasound Nakagami imaging, homodyned-K imaging, and information entropy imaging, is an important group of quantitative ultrasound techniques for characterizing tissue scatterer distribution patterns, such as scatterer concentrations and arrangements. In this study, we proposed a machine learning approach to integrate the strength of multimodality quantitative ultrasound envelope statistics imaging techniques and applied it to detecting microwave ablation induced thermal lesions in porcine liver ex vivo. The quantitative ultrasound parameters included were homodyned-K α which is a scatterer clustering parameter related to the effective scatterer number per resolution cell, Nakagami m which is a shape parameter of the envelope probability density function, and Shannon entropy which is a measure of signal uncertainty or complexity. Specifically, the homodyned-K log10(α), Nakagami-m, and horizontally normalized Shannon entropy parameters were combined as input features to train a support vector machine (SVM) model to classify thermal lesions with higher scatterer concentrations from normal tissues with lower scatterer concentrations. Through heterogeneous phantom simulations based on Field II, the proposed SVM model showed a classification accuracy above 0.90; the area accuracy and Dice score of higher-scatterer-concentration zone identification exceeded 83% and 0.86, respectively, with the Hausdorff distance <26. Microwave ablation experiments of porcine liver ex vivo at 60–80 W, 1–3 min showed that the SVM model achieved a classification accuracy of 0.85; compared with single log10(α),m, or hNSE parametric imaging, the SVM model achieved the highest area accuracy (89.1%) and Dice score (0.77) as well as the smallest Hausdorff distance (46.38) of coagulation zone identification. We concluded that the proposed multimodality quantitative ultrasound envelope statistics imaging based SVM approach can enhance the capability to characterize tissue scatterer distribution patterns and has the potential to detect the thermal lesions induced by microwave ablation.

Web Attack Detection Based on Honeypots and Logistic Regression Algorithm

Web security has emerged as one of the most prominent concerns in the realm of cybersecurity. Traditional rule-based methods for detecting web attacks often rely on manual rule definition and pattern matching, leaving them inadequate in accurately identifying new and intricate attack patterns. In the face of these challenges, machine learning techniques have demonstrated potential and advantages. This paper presents a web attack detection method based on honeypots and the logistic regression algorithm. It involves the cleansing, filtering, and analysis of web logs captured by honeypots, followed by the vectorization of the textual data contained in these logs. The logistic regression algorithm is employed to train and test the classification of the text vectors, generating a logistic regression model. This model is then used to predict newly generated web logs, enabling effective dynamic web attack detection. Experimental evaluations using collected datasets are conducted, comparing the proposed method with the support vector machine approach. The results demonstrate that this method achieves rapid and accurate detection and recognition of web attack behaviors while ensuring performance efficacy.

Waste Prediction Approach Using Hybrid Long Short-Term Memory with Support Vector Machine

As climate change increases the risk of extreme rainfall events, concerns over flood management have also increased. To recover quickly from flood damage and prevent further consequential damage, flood waste prediction is of utmost importance. Therefore, developing a rapid and accurate prediction of flood waste generation is important in order to reduce disaster. Several approaches of flood waste classification have been proposed by various researchers, however only a few focus on prediction of flood waste. In this study, a Long Short-Term Memory (LSTM) and Support Vector Machine (SVM) approach is adapted to address these challenges. Two different raw datasets were obtained from the “Advancing Sustainable Materials Management: Facts and Figures 2015” source. The datasets were for 9 years (1960, 1970, 1980, 1990, 2000, 2005, 2010, 2014, 2015), and are labelled as the materials generated in the Municipal Waste Stream from 1960 to 2015 and the materials Recycled and Composted in Municipal Solid Waste from 1960 to 2015. The waste types were grouped as paper and paperboard (PP), glass (GI), metals (Mt), plastics (PI), rubber and leather (RL), textiles (Tt), wood (Wd), food (Fd), yard trimmings (YT) and miscellaneous inorganic wastes (IW).

Use of CT-derived radiomic features to preoperatively identify invasive mucinous adenocarcinoma in solitary pulmonary nodules ≤3 cm

ObjectiveIn this study, we aimed to utilize computed tomography (CT)-derived radiomics and various machine learning approaches to differentiate between invasive mucinous adenocarcinoma (IMA) and invasive non-mucinous adenocarcinoma (INMA) preoperatively in solitary pulmonary nodules (SPN) ≤3 cm. MethodsA total of 538 patients with SPNs measuring ≤3 cm were enrolled, categorized into either the IMA group (n = 50) or INMA group (n = 488) based on postoperative pathology. Radiomic features were extracted from non-contrast-enhanced CT scans and identified using the least absolute shrinkage and selection operator (LASSO) algorithm. In constructing radiomics-based models, logistic regression, support vector machines, classification and regression trees, and k-nearest neighbors were employed. Additionally, a clinical model was developed, focusing on CT radiological features. Subsequently, this clinical model was integrated with the most effective radiomic model to create a combined model. Performance assessments of these models were conducted, utilizing metrics such as the area under the receiver operating characteristic curve (AUC), DeLong's test, net reclassification index (NRI), and integrated discrimination improvement (IDI). ResultsThe support vector machine approach showed superior predictive efficiency, with AUCs of 0.829 and 0.846 in the training and test cohorts, respectively. The clinical model had AUCs of 0.760 and 0.777 in the corresponding cohorts. The combined model had AUCs of 0.847 and 0.857 in the corresponding cohorts. Furthermore, compared to the radiomic model, the combined model significantly improved performance in both the training (DeLong test P = 0.045, NRI 0.206, IDI 0.024) and test cohorts (P = 0.029, NRI 0.125, IDI 0.032), as well as compared to the clinical model in both the training (P = 0.01, NRI 0.310, IDI 0.09) and test cohorts (P = 0.047, NRI 0.382, IDI 0.085). Conclusionthe combined model exhibited excellent performance in distinguishing between IMA and INMA in SPNs ≤3 cm.

Supplementation of deep neural networks with simplified physics-based features to increase accuracy of plate fundamental frequency predictions

To improve predictive machine learning-based models limited by sparse data, supplemental physics-related features are introduced into a deep neural network (DNN). While some approaches inject physics through differential equations or numerical simulation, improvements are possible using simplified relationships from engineering references. To evaluate this hypothesis, thin rectangular plates were simulated to generate training datasets. With plate dimensions and material properties as input features and fundamental natural frequency as the output, predictive performance of a data-driven DNN-based model is compared with models using supplemental inputs, such as modulus of rigidity. To evaluate model accuracy improvements, these additional features are injected into various DNN layers, and the network is trained with four different dataset sizes. When evaluated against independent data of similar features to the training sets, supplementation provides no statistically-significant prediction error reduction. However, notable accuracy gains occur when independent test data is of material and dimensions different from the original training set. Furthermore, when physics-enhanced data is injected into multiple DNN layers, reductions in mean error from 33.2% to 19.6%, 34.9% to 19.9%, 35.8% to 22.4%, and 43.0% to 28.4% are achieved for dataset sizes of 261, 117, 60, and 30, respectively, demonstrating potential for generalizability using a data supplementation approach. Additionally, when compared with other methods—such as linear regression and support vector machine (SVM) approaches—the physics-enhanced DNN demonstrates an order of magnitude reduction in percentage error for dataset sizes of 261, 117, and 60 and a 30% reduction for a size of 30 when compared with a cubic SVM model independently tested with data divergent from the training and validation set.

A novel fusion Support Vector Machine integrating weak and sphere models for classification challenges with massive data

The unprecedented growth in data generation has necessitated the adoption of advanced analytical techniques. Support Vector Machine (SVM) is a powerful machine learning tool that has proven invaluable in classifying observations through optimal hyperplane in higher dimensions. Despite their widespread use, SVM models encounter substantial challenges during the learning phase with massive datasets, necessitating strategic modifications. This paper introduces a novel fusion methodology incorporating weak and sphere support vector machine to address classification challenges with massive datasets. Comparative analyses across diverse simulated and benchmark real datasets underscore the efficacy of the proposed methodologies, exhibiting sustained predictive performance. The remarkable efficiency gain is noteworthy, as the learning phase requires only 10% of the computation time compared to conventional SVM approaches.

Fault Detection and Diagnosis in Electric Vehicle Systems using IoT and Machine Learning: A Support Vector Machine Approach

This research examines blame discovery and determination in electric vehicle (EV) frameworks utilizing Internet of Things (IoT) information and machine learning calculations, centring on a Support Vector Machine (SVM) approach. The study points to improving the unwavering quality and security of EV operations by precisely recognizing and diagnosing flaws in real time. The test comes about illustrates the adequacy of the SVM-based approach, with an exactness of 95%, accuracy of 94%, review of 96%, and F1-score of 95%. Comparative investigation with elective calculations such as k-Nearest Neighbors, Decision Tree, and Random Forest underscores the predominant execution of SVM in blame discovery and determination. The SVM calculation shows negligible misclassifications over distinctive blame classes, highlighting its strength and viability. This inquiry contributes to the headway of blame location strategies in EV frameworks and gives profitable bits of knowledge into the commonsense usage of machine learning strategies for improving framework unwavering quality. Moving forward, the discoveries clear the way for assist investigations in optimizing blame location systems and expanding their appropriateness to other spaces such as mechanical mechanization and renewable vitality frameworks.

Support Vector Machine Approaches for Tumor Classification and Survival Prediction in Cancer Patients: A Multi-Omics Data Analysis

This study examines the viability of Support Vector Machine (SVM) calculations in tumour classification and survival forecast utilizing multi-omics information investigation in cancer patients. Leveraging a comprehensive dataset comprising genomic, transcriptomic, proteomic, and metabolomics profiles from assorted cancer sorts, we compared four SVM variations: Direct SVM, Polynomial SVM, Radial Basis Function (RBF) SVM, and Sigmoid SVM. Results illustrated that the RBF SVM calculation displayed predominant execution in tumour classification, accomplishing an exactness of 92%, with accuracy, review, and F1 score values of 91%, 94%, and 92% respectively. For survival forecast, the RBF SVM too beat other variations with a concordance file (C-Index) of 78%. These discoveries highlight the potential of SVM approaches in leveraging multi-omics information to move forward with cancer determination and forecast. Our consideration contributes to the developing body of research in machine learning-based cancer investigation and underscores the significance of coordination of different atomic datasets for personalized oncology.

Data reduction for SVM training using density-based border identification.

Numerous classification and regression problems have extensively used Support Vector Machines (SVMs). However, the SVM approach is less practical for large datasets because of its processing cost. This is primarily due to the requirement of optimizing a quadratic programming problem to determine the decision boundary during training. As a result, methods for selecting data instances that have a better likelihood of being chosen as support vectors by the SVM algorithm have been developed to help minimize the bulk of training data. This paper presents a density-based method, called Density-based Border Identification (DBI), in addition to four different variations of the method, for the lessening of the SVM training data through the extraction of a layer of border instances. For higher-dimensional datasets, the extraction is performed on lower-dimensional embeddings obtained by Uniform Manifold Approximation and Projection (UMAP), and the resulting subset can be repetitively used for SVM training in higher dimensions. Experimental findings on different datasets, such as Banana, USPS, and Adult9a, have shown that the best-performing variations of the proposed method effectively reduced the size of the training data and achieved acceptable training and prediction speedups while maintaining an adequate classification accuracy compared to training on the original dataset. These results, as well as comparisons to a selection of related state-of-the-art methods from the literature, such as Border Point extraction based on Locality-Sensitive Hashing (BPLSH), Clustering-Based Convex Hull (CBCH), and Shell Extraction (SE), suggest that our proposed methods are effective and potentially useful.

Label-Free SERS of Urine Components: A Powerful Tool for Discriminating Renal Cell Carcinoma through Multivariate Analysis and Machine Learning Techniques.

The advent of Surface-Enhanced Raman Scattering (SERS) has enabled the exploration and detection of small molecules, particularly in biological fluids such as serum, blood plasma, urine, saliva, and tears. SERS has been proposed as a simple diagnostic technique for various diseases, including cancer. Renal cell carcinoma (RCC) ranks as the sixth most commonly diagnosed cancer in men and is often asymptomatic, with detection occurring incidentally. The onset of symptoms typically aligns with advanced disease, aggressive histology, and unfavorable prognosis, and therefore new methods for an early diagnosis are needed. In this study, we investigated the utility of label-free SERS in urine, coupled with two multivariate analysis approaches: Principal Component Analysis combined with Linear Discriminant Analysis (PCA-LDA) and Support Vector Machine (SVM), to discriminate between 50 RCC patients and 44 healthy donors. Employing LDA-PCA, we achieved a discrimination accuracy of 100% using 13 principal components, and an 88% accuracy in discriminating between different RCC stages. The SVM approach yielded a training accuracy of 100%, a validation accuracy of 99% for discriminating between RCC and controls, and an 80% accuracy for discriminating between stages. The comparative analysis of raw and normalized SERS spectral data shows that while raw data disclose relative concentration variations in urine metabolites between the two classes, the normalization of spectral data significantly improves the accuracy of discrimination. Moreover, the selection of principal components with markedly distinct scores between the two classes serves to alleviate overfitting risks and reduces the number of components employed for discrimination. We obtained the accuracy of the discrimination between the RCC patients cases and healthy donors of 90% for three PCs and a linear discrimination function, and a 88% accuracy of discrimination between stages using six PCs, mitigating practically the risk of overfitting and increasing the robustness of our analysis. Our findings underscore the potential of label-free SERS of urine in conjunction with chemometrics for non-invasive and early RCC detection.

Data-Driven Analytical Model Using Machine Learning Algorithms

The objective of this article is to use machine learning technology, specifically the Support Vector Machine (SVM) approach with a linear kernel, to analyze and predict clean and healthy living behavior (CHLB) in coastal dwellings in Surabaya City. To train the SVM model, researchers collect health and environmental data from the region. As a result, our model predicts house CHLB status with an 83% accuracy rate. The most important variables in this prediction are the amount of community access to appropriate sanitary facilities, the health of households, and the sustainability of public areas that meet health requirements. These findings have crucial implications for attempts to improve CHLB in Surabaya's coastal areas in compliance with the National Medium-Term Development Plan (RPJMN) aims. Furthermore, the findings of this study can be used to build more targeted and long-term health policies in coastal communities.

ENSEMBLE RESAMPLING SUPPORT VECTOR MACHINE, MULTINOMIAL REGRESSION TO MULTICLASS IMBALANCED DATA

Imbalanced data is a commonly encountered issue in classification analysis. This issue gives rise to prediction errors in the classification process, which in turn affects the sensitivity, particularly in the minority class. Resampling techniques can be employed as a means to mitigate the issue of Imbalanced data. Furthermore, ensemble approaches are Utilized in the classification procedure to augment the performance of classification. The present study assesses the efficacy of the bagging ensemble approach in conjunction with ADASYN as a means of addressing the aforementioned issue. The dataset Utilized in this work comprises Imbalanced Glass Identification data, Imbalanced Iris data, and Imbalanced synthetic data. The study Centres on the Utilization of Support Vector Machines (SVM) with parameter optimization using repeated cross-validation (k = 10) and the application of multinomial regression. The evaluation of classification outcomes involves a comparison between the ensemble technique and multinomial regression. This comparison is conducted under pre- and post-resampling conditions, with the evaluation metrics being accuracy, sensitivity, and specificity. The analysis of classification outcomes across the three datasets suggests that the ensemble resampling SVM approach and multinomial regression exhibit superior performance compared to the ensemble SVM and multinomial regression approaches when applied to non-resampled data. Resampling of data has been observed to enhance sensitivity, particularly in the minority class.

Efficient Iot -Machine Learning Based Smart Irrigation Using Support Tree Algae Algorithm

The utilisation of irrigation, one of the most water-intensive agricultural techniques worldwide, has grown in popularity over time. Smart irrigation methods are comparatively innovative technologies that improve domestic landscape irrigation plans, reducing water usage and potential contamination. The primary determinant of agricultural output is soil moisture, and irrigation management depends on a precise estimate of this criterion. The decision-making tool for Irrigation Schedule Prediction available in Machine Learning (ML) plays a crucial role. The drawbacks of traditional machine learning techniques are that they don't predict future values, reduce relative error, and decrease the effective estimation of soil moisture. To overcome the above-said drawbacks, we proposed a machine learning-based SupportTree Algae Algorithm (STAA) to presage soil wetness for smart irrigation. Our proposed STAA method consists of a hybrid approach of Support Vector Machine (SVM) and Decision Tree (DT)classifier incorporated with Artificial Algae Optimization. Our proposed method simulated and achieves 99.5% accuracy, 98.4% precision, 97.5% specificity, and 99.2% Sensitivity when compared with existing methods, namely Random Forest (RF), Fuzzy Logic, and K-Nearest Neighbour (KNN). As a result, a novel STAA method ensured better performance concerning Precision, Sensitivity, Accuracy, Relative Error, Root Mean Square Error (RMSE), Mean Square Error (MSE), Mean Squared Logarithmic Error (MSLE), and Specificity over existing methods.

Diagnostic machine learning applications on clinical populations using functional near infrared spectroscopy: a review.

Functional near-infrared spectroscopy (fNIRS) and its interaction with machine learning (ML) is a popular research topic for the diagnostic classification of clinical disorders due to the lack of robust and objective biomarkers. This review provides an overview of research on psychiatric diseases by using fNIRS and ML. Article search was carried out and 45 studies were evaluated by considering their sample sizes, used features, ML methodology, and reported accuracy. To our best knowledge, this is the first review that reports diagnostic ML applications using fNIRS. We found that there has been an increasing trend to perform ML applications on fNIRS-based biomarker research since 2010. The most studied populations are schizophrenia (n=12), attention deficit and hyperactivity disorder (n=7), and autism spectrum disorder (n=6) are the most studied populations. There is a significant negative correlation between sample size (>21) and accuracy values. Support vector machine (SVM) and deep learning (DL) approaches were the most popular classifier approaches (SVM=20) (DL=10). Eight of these studies recruited a number of participants more than 100 for classification. Concentration changes in oxy-hemoglobin (ΔHbO) based features were used more than concentration changes in deoxy-hemoglobin (ΔHb) based ones and the most popular ΔHbO-based features were mean ΔHbO (n=11) and ΔHbO-based functional connections (n=11). Using ML on fNIRS data might be a promising approach to reveal specific biomarkers for diagnostic classification.

Characterising TOI-732 b and c: New insights into the M-dwarf radius and density valley

Context. TOI-732 is an M dwarf hosting two transiting planets that are located on the two opposite sides of the radius valley. Inferring a reliable demographics for this type of systems is key to understanding their formation and evolution mechanisms. Aims. By doubling the number of available space-based observations and increasing the number of radial velocity (RV) measurements, we aim at refining the parameters of TOI-732 b and c. We also use the results to study the slope of the radius valley and the density valley for a well-characterised sample of M-dwarf exoplanets. Methods. We performed a global Markov chain Monte Carlo analysis by jointly modelling ground-based light curves and CHEOPS and TESS observations, along with RV time series both taken from the literature and obtained with the MAROON-X spectrograph. The slopes of the M-dwarf valleys were quantified via a support vector machine (SVM) procedure. Results. TOI-732b is an ultrashort-period planet (P = 0.76837931-0.00000042+0.0000039 days) with a radius Rb = 1.325-0.058+0.057R⊕, a mass Mb = 2.46 ± 0.19 M⊕, and thus a mean density ρb = 5.8-0.8+1.0 g cm-3, while the outer planet at P = 12.252284 ± 0.000013 days has Rc = 2.39-0.11+0.10R⊕, Mc = 8.04-0.48+0.50M⊕, and thus ρc = 3.24-0.43+0.55 g cm-3. Even with respect to the most recently reported values, this work yields uncertainties on the transit depths and on the RV semi-amplitudes that are smaller up to a factor of ~1.6 and ~2.4 for TOI-732 b and c, respectively. Our calculations for the interior structure and the location of the planets in the mass-radius diagram lead us to classify TOI-732 b as a super-Earth and TOI-732 c as a mini-Neptune. Following the SVM approach, we quantified d log Rp,valley / d logP = -0.065-0.013+0.024, which is flatter than for Sun-like stars. In line with former analyses, we note that the radius valley for M-dwarf planets is more densely populated, and we further quantify the slope of the density valley as d log ρ^valley / d log P = -0.02-0.04+0.12. Conclusions. Compared to FGK stars, the weaker dependence of the position of the radius valley on the orbital period might indicate that the formation shapes the radius valley around M dwarfs more strongly than the evolution mechanisms.