Support Vector Machine Method Research Articles

Porosity identification using residual PPTransformer network

Precisely estimating the carbonate’s porosity is essential for subsurface reservoir characterization. However, conventional methods for obtaining porosity using either core measurements or logging interpretation are expensive and inefficient. Considering the sequence data feature of logging curves and the booming development of intelligent networks in geoscience, this study proposes a reliable and low-cost intelligent Porosity Prediction Transformer (PPTransformer) framework for reservoir porosity prediction using logging curves as inputs. PPTransformer network not only extracts global features through convolutional layers but also captures local features using Encoders and self-attention mechanisms. This proposed network is a data-driven supervised learning framework with a superior accuracy and robustness. The testing results demonstrate that compared to the Transformer network, Long Short-Term time series network, and support vector machine method, the PPTransformer framework exhibits the highest average correlation coefficient and determination coefficient indicators and the lowest root mean square error and absolute error indicators. Moreover, adding stratigraphic lithology as geological constraints to the PPTransformer framework further improves the prediction performance. This indicates that geological constraints will enhance network performance.

Analyzing Twitter Sentiments on Booster Vaccination with Support Vector Machine (SVM) Method

The Indonesian government has implemented various measures to prevent the spread of the COVID-19 virus, one of which is through a vaccination program with two doses (the first dose and the second dose). However, new variants of the virus have emerged, reducing the effectiveness of the initial vaccinations. To address this, the government introduced a booster vaccination program aimed at enhancing immunity by up to 80%. The government's plan for booster vaccination has received both positive and negative opinions from the public through various media platforms, including Twitter. This study analyzes public opinions on the booster vaccination plan into three classes: positive, negative, and neutral. SVM is a classification method in machine learning categorized as supervised learning, which involves finding an optimal line (hyperplane) as a separator for two different data classes. The stages of this research include data collection, data cleaning, data transformation, and data classification using the Support Vector Machine (SVM) method. The results of this study indicate that the accuracy of the SVM model reaches 80.42%.

Comparative study of machine learning methods for mapping forest fire areas using Sentinel-1B and 2A imagery

The study focuses on identifying fireburning and burnt areas in a large-scale forest fire that occurred in Xintian County, China, in October 2022. To investigate the adaptability of machine learning methods in various scenarios for mapping forest fire areas, this study presents a comparative study on the recognition and mapping accuracy of three machine learning algorithms, namely, Support Vector Machine (SVM), Random Forest (RF), and Neural Network (NN), based on Sentinel-1B and 2A imagery. Initially, three sets of pre-fire, during-fire, and post-fire remote sensing data were preprocessed. Various feature parameters from Sentinel-1B and 2A imagery were combined to identify firerelated land cover types. The experimental results revealed that: (i) During the pre-fire period, the SVM method demonstrated superior accuracy compared to the other two methods. The combination of spectral and Normalized Difference Vegetation Index (NDVI) features achieved an optimal accuracy for identifying forest areas with an overall accuracy (OA) of 93.52%. (ii) In the during-fire period, RF method exhibited higher accuracy compared to the other two methods with peak fire identification accuracy reached by combining spectral and Normalized Burn Ratio (NBR) index features at an OA of 95.43%. (iii) In the post-fire period, SVM demonstrated superior accuracy compared to other methods. The highest accuracy of 94.97% was achieved when combining spectral and radar features from Sentinel-1B imagery, highlighting the effectiveness of using spectral and radar backward scattering coefficients as feature parameters to enhance forest fire recognition accuracy for burnt areas. These findings suggest that appropriate machine learning algorithms should be employed under different conditions to obtain more precise identification of forest fire areas. This study provides technical support and empirical evidence for extracting and mapping forest fire areas while assessing damage caused by fires.

Evaluation of Aeolian Sand Collapsibility Based on Physical Indicators in the Mu Us Desert, China

The collapsibility of aeolian sand has hindered the development of oil and gas resources and the construction of oil and gas stations in the Mu Us Desert. This study considered aeolian sand on the southern edge of the Mu Us Desert as the research object. Based on a water immersion load test, standard penetration test, and indoor geotechnical test, four evaluation indicators were selected, the water content, dry density, void ratio, and saturation. Combined with the support vector machine method, we established a method for evaluating the collapsibility of aeolian sand based on basic physical indicators. The results showed the following: (1) The degree of collapsibility was slight, with a small portion showing no collapsibility. And the load-settlement curve (P-s) was divided into three stages: the linear elastic deformation stage, the elastic–plastic deformation stage, and the collapsible deformation stage. (2) There was a strong relationship between the collapsibility coefficient and the four evaluation indicators for aeolian sand. Based on these indicators, we could accurately predict and evaluate the collapsibility coefficient. (3) Machine learning methods, such as the support vector machine, can effectively solve prediction and evaluation problems between variables when there is no clear mathematical relationship between multiple independent variables and a single dependent variable.

Deep Learning CNN-LSTM Approach for Identifying Welder’s Hand Motion Gestures Using Wearable Sensors

Abstract A welder plays a crucial role in the construction of a new ship. Monitoring the performance of welders involved in the construction of a ship is particularly important for controlling dimensions. he competency and consistency of welders play a vital role, with specific hand movement patterns contributing to welding quality. This study aims to identify individual welders’ hand movement patterns using Deep Learning with CNN-LSTM configurations. Data was collected through IMU motion sensors attached to welders’ wrists, capturing acceleration, angular speed, magnetic force, and electric current changes. The data was classified using CNN-LSTM, which showed higher accuracy than SVM methods. Experimental results indicated an overall classification accuracy of 99.73% for identifying individual welders and 97.07% for determining welding positions.

Enhancing ultrasound-guided brachial plexus nerve localization with ResNet50 and support vector machine

<p>Medical image segmentation and classification plays a vital role in nerve block/region identification, particularly for anesthesiologists relying on instinctual judgments. However, due to patient-specific anatomical variations, these methods sometimes lack precision. This research focuses on addressing the problem, by incorporating novel ensembling method of ResNet-50 and support vector machine (SVM) to achieve segmentation of dataset images and classification of nerve blocks respectively. The said novel ensemble model is trained on a publicly available dataset consisting of more than 16,800 images. The sole purpose of this work is to address the problem of peripheral nerve blocking (PNB) with the usage of ensemble modelling, while achieving the highest possible accuracy. This research will help practitioners in accurately identifying the location of brachial plexus and distinguishing the type of nerve block to be injected – interscalene and supraclavicular. The model, which integrates ResNet50 and SVM classifier, achieved a commendable 99.27% accuracy in identifying and classifying the brachial plexus region.</p>

Enhancing breast cancer diagnosis: a comparative analysis of feature selection techniques

Breast cancer is a significant contributor to female mortality, emphasizing the importance of early detection. Predicting breast cancer accurately remains a complex challenge within medical data analysis. Machine learning (ML) algorithms offer valuable assistance in decision-making and diagnosis using medical data. Numerous research studies highlight the effectiveness of ML techniques in improving breast cancer prediction. Feature selection plays a pivotal role in data preprocessing, eliminating irrelevant and redundant features to minimize feature count and improve classification accuracy. This study focuses on optimizing breast cancer diagnostics through feature selection methods, specifically genetic algorithms (GA) and particle swarm optimization (PSO). The research involves a comparative analysis of these methods and the application of a diverse set of ML classification techniques, including logistic regression (LR), support vector machine (SVM), decision tree (DT), and ensemble methods like random forest (RF), AdaBoost, and gradient boosting (GB), using a breast cancer dataset. The models' performance is subsequently evaluated using various performance metrics. The experimental findings illustrate that PSO achieved the highest average accuracy, reaching 99.6% when applied to AdaBoost, while GA attained an accuracy rate of 99.5% when employed with both AdaBoost and RF.

Cloud radon data for earthquake magnitude prediction using machine learning

<span>The study investigates the potential of integrating radon gas concentration telemonitoring systems with machine learning techniques to enhance earthquake magnitude prediction. Conducted in Pacitan, East Java, Indonesia, where the stations are near the active Grundulu fault, the research employs Random Forest (RF), Extreme Gradient Boosting (XGB), Neural Network (NN), AdaBoost (AB), and Support Vector Machine (SVM) methods. Utilizing real-time radon gas concentration measurements, the study aims to refine earthquake magnitude prediction, crucial for disaster preparedness. The evaluation involves multiple metrics like Mean Absolute Error (MAE), Mean Absolute Percentage Error (MAPE), Root Mean Square Error (RMSE), Mean Squared Error (MSE), Symmetric Mean Absolute Percentage Error (SMAPE), and cnSMAPE. XGB and SVM emerge as top performers, showcasing superior predictive accuracy with minimal errors across various metrics. XGB achieved MAE (0.33), MAPE (6.03%), RMSE (0.51), MSE (0.26), SMAPE (0.06), and cnMAPE (0.97), while SVM recorded MAE (0.34), MAPE (6.20%), RMSE (0.51), MSE (0.26), SMAPE (0.06), and cnMAPE (0.97). The analysis reveals XGB as the most effective method, boasting the lowest error values. The study underscores the importance of expanding data availability to enhance predictive models, ultimately contributing to more precise earthquake magnitude predictions and effective mitigation strategies.</span>

Speech Signal Analysis in Patients with Parkinson’s Disease, Taking into Account Phonation, Articulation, and Prosody of Speech

This study involved performing tests to detect Parkinson’s disease (PD) based on voice changes, including speech phonation, articulation, and prosody, in patients with PD using different types of speech signal. For this purpose, during the first stage of the investigation, three separately modeled PD diagnosis systems using different types of speech signal characteristics were defined. The classification results were obtained when the SVM method was applied compared to the k-nearest neighbors method applying 1-nn in general. The tests were carried out within the database of patient voice recordings collected in the Department of Neurology at the Medical University of Warsaw. The second stage of the research was the selection of descriptors. The SFFS (sequential floating forward) method was applied together with the k-nn and SVM classifier. These subsets were used to create a new system based on a descriptor loose integration. Within the experiments conducted, general diagnosis results lead to improved classifier performance only in certain cases. This prompted the authors to conduct the last experimental research stage—selection at the feature fusion stage. Feature evaluation ranking methods (Relief, Fisher Score, F-tests, Chi-square) were applied for this purpose. With 10-fold validation, the k-nn method achieved an recognition rate of 92.2% with 91.1% sensitivity and 93.3% specificity.

Machine Learning Methods in IoT Based Embedded Systems for Classifying Physical Faults in Water Distribution Networks

Water is the most important factor for the survival of living things on Earth. Although 70% of the Earth is water, the amount of drinkable water is approximately 0.3%. Therefore, creating a sustainable water policy and carrying out studies are very important for our world and our future. Most of the potable water resources are physical losses. In the evaluations made based on metropolitan municipalities, it was seen that the water loss rate was approximately 50%. The study aims to find water pipe faults using IoT (Internet of Things) based machine learning classifiers to prevent physical losses in water distribution networks. Within the scope of this study, an experimental environment was created and an IMU (Inertial Measurement Unit) sensor was fixed on plastic pipes of different diameters and lengths. Vibration data collected in different scenarios (pressure, etc. factors) were transferred to the ThingSpeak platform over the internet. The transferred data could be monitored in real-time on a server. Physical damage in the pipes was detected using signal pre-processing, feature extraction, and feature selection algorithms on vibration data. In the study, damages were classified using machine learning-based classification (Decision Trees, k-Nearest Neighbors, Linear Discriminant, Support Vector Machines) methods to predict the type of damage (solid, hole, multi-hole). The data set revealed within the scope of the study is thought to lead to scientific studies in this field. The results obtained are close to the state-of-the-art results.

Classification of plants based on time-series SAR coherence and intensity data in Yancheng coastal wetland

ABSTRACT Investigating coastal wetland plant communities is of great significance for wetland monitoring due to the important functions of coastal wetlands, such as maintaining biodiversity and mitigating global climate change. Current studies on wetland plants mostly rely on optical data, with few utilizing synthetic aperture radar (SAR) data. Moreover, these studies often analysed single temporal SAR data, which limited the exploration of the valuable information present in time-series SAR data. Therefore, in this paper, we proposed a technique for mapping coastal wetland plant types based on time-series SAR coherence and intensity data to fully utilize the information from these data. We utilized Sentinel-1 Single Look Complex (SLC) images covering the Yancheng coastal wetland for the entire year of 2021 to investigate the effectiveness of using dual-polarization interferometric coherence and intensity-derived information from time-series Sentinel-1 data as features for classification. Plant classification was conducted using support vector machine (SVM) and random forest (RF) methods. Our results demonstrated that integrating time-series dual-polarization coherence and intensity-derived information resulted the best classification accuracy, with an overall accuracy (OA) of 89.79% and a Kappa coefficient of 0.858. This highlights the effectiveness of combining coherence and intensity data from time-series Sentinel-1 for monitoring plant cover in coastal wetlands.

Sentiment Analysis of Indonesian Responses to the Conflict in Palestine Using KNN and SVM Methods

The prolonged conflict between Palestine and Israel has attracted worldwide attention, including Indonesia, which has a history of strong support for the Palestinian cause. This study aims to analyze the sentiment of Indonesian people towards the Palestinian-Israeli conflict using the K-Nearest Neighbors (KNN) and Support Vector Machine (SVM) methods. The subject of this research is user data X (Twitter) which contains opinions about the conflict. After preprocessing, weighting, and labeling, 2960 tweets were collected and classified into three sentiment categories: positive, negative, and neutral. The KNN+SVM method is applied to classify the sentiment of the processed tweet data. The results showed that of the 2960 data analyzed, 33.8% were labeled positive, 38.9% were labeled negative, and 27.4% were labeled neutral with 82% accuracy, 83% precision, 82% recall, and 82% F1-Score. These results show that the majority of Indonesians tend to be negative in expressing their views on the Palestinian-Israeli conflict. This analysis provides greater insight into sentiment patterns in Indonesian responses to sensitive issues, and contributes to the study of public opinion and social dynamics on social media.

Resting-state functional magnetic resonance imaging and support vector machines for the diagnosis of major depressive disorder in adolescents

BACKGROUND Research has found that the amygdala plays a significant role in underlying pathology of major depressive disorder (MDD). However, few studies have explored machine learning-assisted diagnostic biomarkers based on amygdala functional connectivity (FC). AIM To investigate the analysis of neuroimaging biomarkers as a streamlined approach for the diagnosis of MDD in adolescents. METHODS Forty-four adolescents diagnosed with MDD and 43 healthy controls were enrolled in the study. Using resting-state functional magnetic resonance imaging, the FC was compared between the adolescents with MDD and the healthy controls, with the bilateral amygdala serving as the seed point, followed by statistical analysis of the results. The support vector machine (SVM) method was then applied to classify functional connections in various brain regions and to evaluate the neurophysiological characteristics associated with MDD. RESULTS Compared to the controls and using the bilateral amygdala as the region of interest, patients with MDD showed significantly lower FC values in the left inferior temporal gyrus, bilateral calcarine, right lingual gyrus, and left superior occipital gyrus. However, there was an increase in the FC value in Vermis-10. The SVM analysis revealed that the reduction in the FC value in the right lingual gyrus could effectively differentiate patients with MDD from healthy controls, achieving a diagnostic accuracy of 83.91%, sensitivity of 79.55%, specificity of 88.37%, and an area under the curve of 67.65%. CONCLUSION The results showed that an abnormal FC value in the right lingual gyrus was effective as a neuroimaging biomarker to distinguish patients with MDD from healthy controls.

Drug–target interaction prediction by integrating heterogeneous information with mutual attention network

BackgroundIdentification of drug–target interactions is an indispensable part of drug discovery. While conventional shallow machine learning and recent deep learning methods based on chemogenomic properties of drugs and target proteins have pushed this prediction performance improvement to a new level, these methods are still difficult to adapt to novel structures. Alternatively, large-scale biological and pharmacological data provide new ways to accelerate drug–target interaction prediction.MethodsHere, we propose DrugMAN, a deep learning model for predicting drug–target interaction by integrating multiplex heterogeneous functional networks with a mutual attention network (MAN). DrugMAN uses a graph attention network-based integration algorithm to learn network-specific low-dimensional features for drugs and target proteins by integrating four drug networks and seven gene/protein networks collected by a certain screening conditions, respectively. DrugMAN then captures interaction information between drug and target representations by a mutual attention network to improve drug–target prediction.ResultsDrugMAN achieved the best performance compared with cheminformation-based methods SVM, RF, DeepPurpose and network-based deep learing methods DTINet and NeoDT in four different scenarios, especially in real-world scenarios. Compared with SVM, RF, deepurpose, DTINet, and NeoDT, DrugMAN showed the smallest decrease in AUROC, AUPRC, and F1-Score from warm-start to Both-cold scenarios. This result is attributed to DrugMAN’s learning from heterogeneous data and indicates that DrugMAN has a good generalization ability. Taking together, DrugMAN spotlights heterogeneous information to mine drug–target interactions and can be a powerful tool for drug discovery and drug repurposing.

Prediction of soil organic carbon and total nitrogen affected by mine using Vis–NIR spectroscopy coupled with machine learning algorithms in calcareous soils

The utilization of visible-near infrared (Vis–NIR) spectroscopy presents a nondestructive, fast, reliable and cost-effective approach to predicting total nitrogen (TN) and organic carbon (OC) levels. This study employed a combination of Vis–NIR spectroscopy, partial least-squares regression (PLSR), and support vector machine (SVM) models to investigate the effects of mining on TN and OC stocks in both the topsoil (0–10 cm) and subsoil (10–40 cm). 105 soil samples were collected from agricultural areas near an iron mine, polluted, moderately-polluted, and non-polluted sites. Results indicated that soils at the non-polluted site had the highest of soil OC stocks (7.5 kg m–2) and total nitrogen (2.5 kg m–2), followed by the moderately-polluted site. Furthermore, it was observed that soils from the polluted site displayed the highest spectral reflectance. The spectral bands in the range of 500–700 nm showed the strongest correlation with soil organic carbon content. Notably, the SVM method utilizing Vis–NIR spectroscopy provided superior predictions for both subsoil and topsoil organic carbon and total nitrogen compared to the PLSR methods. Additionally, SVM demonstrated better performance in predicting topsoil soil organic carbon (R2 = 0.87, RMSE = 0.13%, and RPD = 2.8) and total nitrogen (R2 = 0.91, RMSE = 0.13%, and RPD = 2.4) compared to the subsoil, owing to the larger OM content in the topsoils.

DANA App Sentiment Analysis: Comparison of XGBoost, SVM, and Extra Trees

This research aims to analyze sentiment on DANA application reviews to find out user perceptions by comparing Extreme Gradient Boosting (XGBoost), Support Vector Machine (SVM), and Extra Trees Classifier classification methods. DANA application review data is obtained from the Kaggle site which consists of 50,000 Indonesian-language reviews labeled with positive and negative sentiments. The research stages include data preprocessing to clean and prepare the review text, applying word weighting using Word2Vec to give weight to words based on their context, balancing sentiment classes using SMOTE to address the imbalance of positive and negative review classes. It should be noted that the initial proportion of data before applying SMOTE may affect the results. The data is then divided into training and testing sets, then the models are trained and evaluated using Confusion Matrix and K-Fold Cross-Validation. The results of the three classification methods are measured by the accuracy matrix and F1-Score to assess model performance, the SVM and XGBoost methods obtained an accuracy of 93% and the ETC method achieved an F1-Score value of 96% at K=6, the three models proved to be very accurate in predicting the sentiment of DANA application reviews both positive and negative. The practical implications of this research can identify areas for application improvement, develop popular features, personalize services based on user preferences, and manage application reputation.

Water Level Classification for Detect Flood Disaster Status Using KNN and SVM

Flooding occurs when the water's surface elevation exceeds the average level, overflowing river water and creating inundation in low-lying areas. Early warning for potential floods significantly reduces losses, such as human casualties and property damage. In this context, the flood disaster classification system uses water surface elevation data from the Water Resources Agency to predict the likelihood of floods using the K-Nearest Neighbors (KNN) Algorithm. This research aims to classify flood status based on water surface elevation using the K-Nearest Neighbors and Support Vector Machine(SVM) methods in the Ciliwung River. The study results indicate that the SVM algorithm outperforms the KNN algorithm. The SVM algorithm used parameter C ranging from 1 to 10 in the scenarios, and the RBF kernel achieved 100% accuracy. On the other hand, the KNN algorithm achieved 100% accuracy only for K values of 1, 2, 3, 4, and 5 in scenarios where K ranged from 1 to 10.

Machine learning for improved drought forecasting in Chhattisgarh India: a statistical evaluation

Meteorological drought is one of the major natural hazards that affects the ecosystem of the Central Indian state of Chhattisgarh. This study delves into the analysis, comparison, and prediction of drought trends spanning the period from 1993 to 2023 in the study area. Employing a comprehensive methodology, utilization of the Modified Mann–Kendall test to analyze drought trends, while assessing drought severity through the Standardized Precipitation Index (SPI) and the Standardized Precipitation Evapotranspiration Index (SPEI) has been done. Further research entails assessing the link between SPI and SPEI utilizing the Pearson correlation coefficient and simple linear regression techniques. Additionally, the Support Vector Machine (SVM) and Random Forest (RF) methods were used for predictive modelling feasibility. The findings helped to deepen our understanding of drought dynamics in the region, providing important insights for drought mitigation and adaptation efforts. This study emphasizes the importance of using a variety of statistical techniques and machine learning algorithms to thoroughly analyze, compare, and forecast drought patterns, thereby informing evidence-based decision-making for sustainable water resource management and agricultural planning in Chhattisgarh, India.

Analisis Sentimen Masyarakat terhadap Pelayanan e-KTP dengan Metode Support Vector Machine

The rapid development of information and communication technology allows society to access various information needed in daily life. The Law of the Republic of Indonesia Number 23 of 2006 concerning population administration serves as an important element in population management. Population documents are issued by official institutions and have legal legitimacy as valid evidence. The method used in this research regarding public sentiment towards e-ID card services is the survey method, which aims to collect data from a large population using a smaller sample. The steps or processes in this research using the SVM method consist of case folding, cleaning, tokenizing, normalization, stopword removal, and stemming. Based on the classification of 150 test data using SVM, the number of positive sentiments recorded is 110 opinions, while negative sentiments recorded are 40 opinions.

Prediction of Hydrogen Production from Solid Oxide Electrolytic Cells Based on ANN and SVM Machine Learning Methods

In recent years, the application of machine learning methods has become increasingly common in atmospheric science, particularly in modeling and predicting processes that impact air quality. This study focuses on predicting hydrogen production from solid oxide electrolytic cells (SOECs), a technology with significant potential for reducing greenhouse gas emissions and improving air quality. We developed two models using artificial neural networks (ANNs) and support vector machine (SVM) to predict hydrogen production. The input variables are current, voltage, communication delay time, and real-time measured hydrogen production, while the output variable is hydrogen production at the next sampling time. Both models address the critical issue of production hysteresis. Using 50 h of SOEC system data, we evaluated the effectiveness of the ANN and SVM methods, incorporating hydrogen production time as an input variable. The results show that the ANN model is superior to the SVM model in terms of hydrogen production prediction performance. Specifically, the ANN model shows strong predictive performance at a communication delay time ε = 0.01–0.02 h, with RMSE = 2.59 × 10−2, MAPE = 33.34 × 10−2%, MAE = 1.70 × 10−2 Nm3/h, and R2 = 99.76 × 10−2. At delay time ε = 0.03 h, the ANN model yields RMSE = 2.74 × 10−2 Nm3/h, MAPE = 34.43 × 10−2%, MAE = 1.73 × 10−2 Nm3/h, and R2 = 99.73 × 10−2. Using the SVM model, the prediction error values at delay time ε = 0.01–0.02 h are RMSE = 2.70 × 10−2 Nm3/h, MAPE = 44.01 × 10−2%, MAE = 2.24 × 10−2 Nm3/h, and R2 = 99.74 × 10−2, while at delay time ε = 0.03 h they become RMSE = 2.67 × 10−2 Nm3/h, MAPE = 43.44 × 10−2%, MAE = 2.11 × 10−2 Nm3/h, and R2 = 99.75 × 10−2. With this precision, the ANN model for SOEC hydrogen production prediction has positive implications for air pollution control strategies and the development of cleaner energy technologies, contributing to overall improvements in air quality and the reduction of atmospheric pollutants.