Support Vector Machine Algorithm Research Articles

Magnetic Resonance Imaging Texture Analysis Based on Intraosseous and Extraosseous Lesions to Predict Prognosis in Patients with Osteosarcoma

Objectives: To construct an optimal magnetic resonance imaging (MRI) texture model to evaluate histological patterns and predict prognosis in patients with osteosarcoma (OS). Methods: Thirty-four patients underwent pretreatment MRI and were diagnosed as having OS by surgical resection or biopsy between September 2008 and June 2018. Histological patterns and 3-year survival were recorded. Manual segmentation was performed in intraosseous, extraosseous, and entire lesions on T1-weighted, T2-weighted, and contrast-enhanced T1-weighted images to extract texture features and perform principal component analysis. A support vector machine algorithm with 3-fold cross-validation was used to construct and validate the models. The area under the receiver operating characteristic curve (AUC) was calculated to evaluate diagnostic performance in evaluating histological patterns and 3-year survival. Results: Eight patients were chondroblastic and the remaining twenty-six patients were non-chondroblastic patterns. Twenty-seven patients were 3-year survivors, and the remaining seven patients were non-survivors. In discriminating chondroblastic from non-chondroblastic patterns, the model from extraosseous lesions on the T2-weighted images showed the highest diagnostic performance (AUCs of 0.94 and 0.89 in the training and validation sets). The model from intraosseous lesions on the T1-weighted images showed the highest diagnostic performance in discriminating 3-year non-survivors from survivors (AUCs of 0.99 and 0.88 in the training and validation sets) with a sensitivity, specificity, positive predictive value, and negative predictive value of 85.7%, 92.6%, 75.0%, and 96.2%, respectively. Conclusions: The texture models of extraosseous lesions on T2-weighted images can discriminate the chondroblastic pattern from non-chondroblastic patterns, while the texture models of intraosseous lesions on T1-weighted images can discriminate 3-year non-survivors from survivors.

Prediction of 12-month recurrence of pancreatic cancer using machine learning and prognostic factors.

Pancreatic cancer is lethal and prevalent among other cancer types. The recurrence of this tumor is high, especially in patients who did not receive adjuvant therapies. Early prediction of PC recurrence has a significant role in enhancing patients' prognosis and survival. So far, machine learning techniques have given us insight into favorable performance efficiency in various medical domains. So, this study aims to establish a prediction model based on machine learning to achieve better prediction on this topic. In this retrospective research, we used data from 585 PC patient cases from January 2019 to November 2023 from three clinical centers in Tehran City. Ten chosen ensemble and non-ensemble algorithms were used to establish prediction models on this topic. Random forest and support vector machine with an AU-ROC of approximately 0.9 obtained more performance efficiency regarding PC recurrence. Lymph node metastasis, tumor size, tumor grade, radiotherapy, and chemotherapy were the best factors influencing PC recurrence. Random forest and support vector machine algorithms demonstrated high-performance ability and clinical usability to improve doctors' decisions in achieving different therapeutic and diagnostic measures.

Individualized post-operative prediction of cochlear implantation outcomes in children with prelingual deafness using functional near-infrared spectroscopy.

The goal of this study was to develop an objective measure and predictor of cochlear implantation (CI) outcomes using functional near-infrared spectroscopy (fNIRS) for young children with prelingual deafness. Sound-evoked hemodynamic responses were recorded from auditory and language-related cortical regions of 47 child CI recipients (35.47 ± 17.24 months of age) using fNIRS shortly after CI activation (0.26 ± 0.30 months). There were four sound conditions (natural speech, instrumental music, multi-speaker babble noise, and speech-in-noise). Post-CI auditory and verbal communication performance was evaluated using clinical questionnaires with caretakers. Both classification and individualized regression models were constructed to predict post-CI behavioral improvement from fNIRS data using support vector machine (SVM) learning algorithms. Auditory cortical responses shortly after CI hearing onset yielded highly accurate prediction of behavioral development in young CI children. For classification models, optimal prediction was achieved using cortical responses to two or more sound conditions, with the highest accuracy of 98.20% (precision = 98.17%, sensitivity = 98.96%, area under the curve of the receiver operating characteristic curve = 99.61%) obtained with the combination of speech, noise, and music stimuli. Similarly, for regression models, best prediction of individual development was achieved using three (highest r = 0.919) or four (r = 0.966) sound conditions. The predictability of cortical responses far outperformed (Cohen's d: 18.56) that of the collection of audiological and demographic parameters (classification accuracy: 0.62) under the same SVM algorithms and could not benefit from the inclusion of the latter. Machine learning models using auditory cortical hemodynamic responses shortly after CI activation were able to predict individualized post-CI behavioral improvement in children with prelingual deafness. Level 5.

A Space-Efficient One-Pass Online SVM Algorithm

In this paper we consider the problem of training a Support Vector Machine (SVM) online using a stream of data in random order. We provide a fast online training algorithm for general SVM on very large datasets. Based on the geometric interpretation of SVM known as the polytope distance, our algorithm uses a gradient descent procedure to solve the problem. With high probability our algorithm outputs an [Formula: see text]-approximation result in constant time and space, which is independent of the size of the dataset, where [Formula: see text]-approximation means that the separating margin of the classifier is almost optimal (with error [Formula: see text]), and the number of misclassified training points is very small (with error [Formula: see text]). Experimental results show that our algorithm outperforms most of existing online algorithms, especially in the space requirement aspect, while maintaining high accuracy.

Distinguishing lymphoma from benign lymph node diseases in fever of unknown origin using PET/CT radiomics.

A considerable portion of patients with fever of unknown origin (FUO) present concomitant lymphadenopathy. Diseases within the spectrum of FUO accompanied by lymphadenopathy include lymphoma, infections, and rheumatic diseases. Particularly, lymphoma has emerged as the most prevalent etiology of FUO with associated lymphadenopathy. Distinguishing between benign and malignant lymph node lesions is a major challenge for physicians and an urgent clinical concern for patients. However, conventional imaging techniques, including PET/CT, often have difficulty accurately distinguishing between malignant and benign lymph node lesions. This study utilizes PET/CT radiomics to differentiate between lymphoma and benign lymph node lesions in patients with FUO, aiming to improve diagnostic accuracy. Data were collected from 204 patients who underwent 18F-FDG PET/CT examinations for FUO, including 114 lymphoma patients and 90 patients with benign lymph node lesions. Patients were randomly divided into training and testing groups at a ratio of 7:3. A total of 15 effective features were obtained by the least absolute shrinkage and selection operator (LASSO) algorithm. Machine learning models were constructed using logistic regression (LR), support vector machine (SVM), random forest (RF), and k-nearest neighbors (KNN) algorithms. In the training group, the area under the curve (AUC) values for predicting lymphoma and benign cases by LR, SVM, RF, and KNN models were 0.936, 0.930, 0.998, and 0.938, respectively. There were statistically significant differences in AUC between the RF and other models (all P < 0.001). In the testing group, the AUC values for the four models were 0.860, 0.866, 0.915, and 0.891, respectively, with no statistically significant differences observed among them (all P > 0.05). The decision curve analysis (DCA) curves of the RF model outperformed those of the other three models in both the training and testing groups. PET/CT radiomics demonstrated promising performance in discriminating lymphoma from benign lymph node lesions in patients with FUO, with the RF model showing the best performance.

Determining the Effect of Fear of Illness and Virus Evaluation and Quality of Life on Diagnosis of Social Phobia in Patients With Chronic Disease: Using Machine Learning Approaches.

While the SARS-CoV-2 pandemic and other epidemics continue, individuals with chronic diseases and those over the age of 60 are most affected by the psychological effects. This research is the first and most crucial study comparing the quality of life, physical activities, fear of disease and virus evaluation, and social phobia in chronic patients and healthy individuals, and modeling the classification of social phobia using the machine learning approach. The quantitative study used STROBE guidelines for the correlational and cross-sectional design. The research questionnaire was designed in four parts: a personal information form, the Liebowitz Social Phobia Scale, the Fear of Illness and Virus Evaluation Scale, and the Quality of Life Scale (EUROHIS-WHOQOL-8). Different algorithms were examined using the machine learning approach to classify social phobia. More participants were reached than the calculated sample size (n = 1068) using simple random sampling, and the final sample size was 1235. Patients with chronic diseases had lower physical activity levels and quality of life scores. Patients with chronic diseases (n=728) had higher Fear of Illness and Virus Evaluation Scale-35 scores and Liebowitz Social Phobia Scale-24 scores compared to healthy participants (n=507) and lower physical activity levels (3.901 ± 3.035) and quality of life scores (29.016 ± 4.782). Two algorithms (K-nearest neighbors and support vector machine algorithm) provided the best performance. In support vector machine algorithm, Fear of Illness and Virus Evaluation Scale-35 was the most critical feature in classifying social phobia. Physical activity level and Liebowitz Social Phobia Scale seem to be positively related in k-nearest neighbors. The model is essential for identifying and understanding social phobia factors in patients with chronic diseases. Support vector machine algorithm is an algorithm that is preferred for identifying patients at risk of fear and will facilitate follow-up when integrated into smartphone applications.

Abstract 4118342: Acoustic Analysis For The Detection Of Leaflet Thrombosis After Transcatheter Aortic Valve Replacement

Introduction: Following trans-catheter aortic valve replacement (TAVR), patients may develop aortic valve leaflet thrombosis, a condition associated with an increased risk of embolic events. Currently, the diagnosis of post-TAVR leaflet thrombosis is based on echocardiography surveillance or cardiac tomography (CCT) scan, both require specialized team and equipment, and may also expose the patients to radiation and contrast. Acoustic analysis is a non-invasive reproducible method, which incorporates the recording of cardiac sounds and analyzing them via machine learning algorithms. Here, we investigated the diagnostic abilities of acoustic analysis in the detection of post-TAVR leaflet thrombosis. Methods: Using an electronic stethoscope, heart sounds were prospectively recorded at 2 time points: 24-hours and 6-months post-TAVR. CCT scan was performed 6-months following TAVR to detect leaflet thrombosis. Acoustic sounds were analyzed, using a Gaussian support vector machine (SVM) algorithm, to identify features associated with leaflet thrombosis. Results: Of 19 consecutive patients, 3 were found to have high-grade leaflet thrombosis based on CCT results. The SVM algorithm effectively classified heart sounds into "normal" and "thrombotic", with a sensitivity of 100% and specificity of 97.2%. Following anticoagulation therapy, all 3 patients showed no signs of leaflet thrombosis on follow-up CCT scans and were also classified as "normal" by the algorithm. Notably, at the time of leaflet thrombosis, Doppler echocardiographies showed normal pressure gradients across the affected valves. Conclusions: These initial results suggest that acoustic analysis, combined with machine learning algorithms, may identify post-TAVR leaflet thrombosis, providing a non-invasive, cost-effective, and radiation-free alternative to traditional diagnostic methods.

Hybrid Machine Learning Approaches for 5G Traffic Prediction

ABSTRACT Accurate traffic prediction poses great difficulties because of the continuously increasing scale and diversity of 5G network traffic, which is driven by user demands. Moreover, certain characteristics of 5G traffic are constantly changing; thus, simulations using traditional models often lead to incorrect estimations or inefficient utilization of available resources. Consequently, we propose a hybrid machine learning model that integrates support vector machine (SVM) and decision tree algorithms to enhance efficiency of 5G traffic prediction. The structure of the hybrid model dynamically adjusts by adding or removing hidden layers and units within the network to improve prediction performance. The efficacy of the proposed model is evaluated using metrics like mean squared error, mean absolute error, and root mean squared error (RMSE). Findings show that the hybrid model consistently achieves lower error rates than SVM alone. Further performance enhancement of the hybrid model in predicting 5G traffic is also supported by comparisons of R-squared values against signal-to-noise ratios. These outcomes show the potential of the proposed method to improve traffic prediction accuracy in 5G networks, serving as a powerful tool for network control.

Handheld NIR Spectroscopy Combined with a Hybrid LDA-SVM Model for Fast Classification of Retail Milk

The EU market offers different types of milk, distinguished by origin, production method, processing technology, fat content, and other characteristics, which are often detailed on product labels. In this context, ensuring the authenticity of milk is crucial for maintaining standards and preventing fraud. Various food authenticity techniques have been employed to achieve this. Among them, near-infrared (NIR) spectroscopy is valued for its non-destructive and rapid analysis capabilities. This study evaluates the effectiveness of a miniaturized NIR device combined with support vector machine (SVM) algorithms and LDA feature selection to discriminate between four commercial milk types: high-quality fresh milk, milk labeled as mountain product, extended shelf-life milk, and TSG hay milk. The results indicate that NIR spectroscopy can effectively classify milk based on the type of milk, relying on different production systems and heat treatments (pasteurization). This capability was greater in distinguishing high-quality mountain and hay milk from the other types, while resulting in less successful class assignment for extended shelf-life milk. This study demonstrated the potential of portable NIR spectroscopy for real-time and cost-effective milk authentication at the retail level.

Machine Learning Approaches for the Fusion of Near-Infrared, Mid-Infrared, and Raman Data to Identify Cartilage Degradation in Human Osteochondral Plugs.

Vibrational spectroscopy methods such as mid-infrared (MIR), near-infrared (NIR), and Raman spectroscopies have been shown to have great potential for in vivo biomedical applications, such as arthroscopic evaluation of joint injuries and degeneration. Considering that these techniques provide complementary chemical information, in this study, we hypothesized that combining the MIR, NIR, and Raman data from human osteochondral samples can improve the detection of cartilage degradation. This study evaluated 272 osteochondral samples from 18 human knee joins, comprising both healthy and damaged tissue according to the reference Osteoarthritis Research Society International grading system. We established the one-block and multi-block classification models using partial least squares discriminant analysis (PLSDA), random forest, and support vector machine (SVM) algorithms. Feature modeling by principal component analysis was tested for the SVM (PCA-SVM) models. The best one-block models were built using MIR and Raman data, discriminating healthy cartilage from damaged with an accuracy of 77.5% for MIR and 77.8% for Raman using the PCA-SVM algorithm, whereas the NIR data did not perform as well achieving only 68.5% accuracy for the best model using PCA-SVM. The multi-block approach allowed an improvement with an accuracy of 81.4% for the best model by PCA-SVM. Fusing three blocks using MIR, NIR, and Raman by multi-block PLSDA significantly improved the performance of the single-block models to 79.1% correct classification. The significance was proven by statistical testing using analysis of variance. Thus, the study suggests the potential and the complementary value of the fusion of different spectroscopic techniques and provides valuable data analysis tools for the diagnostics of cartilage health.

Trend‐Based Predictive Maintenance and Fault Detection Analytics for Photovoltaic Power Plants

Optimized predictive maintenance in photovoltaic (PV) systems is crucial for ensuring prolonged operational performance and cost‐effective operation and maintenance (O&amp;M). Even though failure detection methods have already been developed, the main challenge remains the lack of predictive maintenance strategies to accurately forecast underperformance conditions. The scope of this work is to develop a predictive maintenance and failure detection routine for assessing the health status of PV systems. The workflow consists of the eXtreme gradient boosting algorithm for modeling the PV performance, the one‐class support vector machine algorithm for fault detection, and the Facebook Prophet algorithm for forecasting PV performance trends and generating maintenance alerts. The developed data‐driven routine analyzes performance trend deviations and it is validated using a historical dataset from a utility‐scale PV power plant in Greece. The obtained results show the effectiveness of the developed workflow in detecting fault conditions, achieving a sensitivity of 96.9%. Additionally, the results demonstrate the workflow's ability to generate predictive maintenance alerts up to 7 days in advance, yielding a sensitivity of 92.9%. Finally, the study provides useful insights that enhance operators’ efficiency in conducting O&amp;M activities.

Intelligent Inversion Analysis of Surrounding Rock Parameters and Deformation Characteristics of a Water Diversion Surge Shaft

The water diversion surge shaft is vital for a hydropower station. However, the complex geological properties of the surrounding rock make it challenging to obtain its mechanical parameters. A method combining particle swarm optimization (PSO) and support vector machine (SVM) algorithms is proposed for estimating these parameters. According to the engineering geological background and support scheme, a three-dimensional model of the water diversion surge shaft is established by FLAC3D. An orthogonal test is designed to verify the accuracy of the numerical model. Then, the surrounding rock mechanical parameter database is established. The PSO-SVM intelligent inversion algorithm is used to invert the optimal values of the mechanical parameters of the surrounding rock. The support for excavating the next layer depends on the mechanical parameters of the current rock layer. An optimized design scheme is then compared and analyzed with the original support scheme by considering deformation and plastic characteristics. The research results demonstrate that the PSO-SVM intelligent inversion algorithm can effectively improve the accuracy and efficiency of the inversion of rock mechanical parameters. Under the influence of excavation, the surrounding rock in the plastic zone mainly fails in shear, with maximum deformation occurring in the middle and lower parts of the excavation area. The maximum deformation of the surrounding rock under support with long anchor cables is 0.6 cm less than that of support without long anchor cables and 4.07 cm less than that of support without an anchor. In the direction of the maximum and minimum principal stress, the maximum depth of the plastic zone under the support with long anchor cables is 1.3 m to 2.6 m less than that of the support without long anchor cables and the support without an anchor. Compared with the support without long anchor cables and support without an anchor, the support with long anchor cables can effectively control the deformation of the surrounding rock and limit the development of the plastic zone.

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.

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.

PET/computed tomography radiomics combined with clinical features in predicting sarcopenia and prognosis of diffuse large B-cell lymphoma.

The study aimed to assess the role of 18F-fluorodeoxyglucose (FDG) PET/computed tomography (CT) radiomics combined with clinical features using machine learning (ML) in predicting sarcopenia and prognosis of patients with diffuse large B-cell lymphoma (DLBCL). A total of 178 DLBCL patients (118 and 60 applied for training and test sets, respectively) who underwent pretreatment 18F-FDG PET/CT were retrospectively enrolled. Clinical characteristics and PET/CT radiomics features were analyzed, and feature selection was performed using univariate logistic regression and correlation analysis. Sarcopenia prediction models were built by ML algorithms and evaluated. Besides, prognostic models were also developed, and their associations with progression-free survival (PFS) and overall survival (OS) were identified. Fourteen features were finally selected to build sarcopenia prediction and prognosis models, including two clinical (maximum standard uptake value of muscle and BMI), nine PET (seven gray-level and two first-order), and three CT (three gray-level) radiomics features. Among sarcopenia prediction models, combined clinical-PET/CT radiomics features models outperformed other models; especially the support vector machine algorithm achieved the highest area under curve of 0.862, with the sensitivity, specificity, and accuracy of 79.2, 83.3, and 78.3% in the test set. Furthermore, the consistency index based on the prognostic models was 0.753 and 0.807 for PFS and OS, respectively. The enrolled patients were subsequently divided into high-risk and low-risk groups with significant differences, regardless of PFS or OS (P < 0.05). ML models incorporating clinical and PET/CT radiomics features could effectively predict the presence of sarcopenia and assess the prognosis in patients with DLBCL.

Vehicle Lane Changing Game Model Based on Improved SVM Algorithm

In order to improve the autonomous lane-changing performance of unmanned vehicles, this paper aims to solve the problem of inaccurate decision classification in traditional support vector machine (SVM) algorithms applied to the lane-changing decision-making stage of intelligent driving vehicles. By using game theory-related theories and combining the improved support vector machine (SSA-SVM) method, a vehicle autonomous lane-changing strategy based on game theory is established. The optimized SVM method has certain advantages for vehicle lane-changing decision-making with a small sample size in actual production processes. The lane-changing decision judgment accuracy rate of the SSA-SVM algorithm model can reach 93.6% compared with the SVM algorithm model without algorithm optimization; the SSA-SVM algorithm model has obvious advantages in decision performance and running speed. Therefore, the proposed new algorithm can effectively solve the problem of the objective consideration of the payoff function in conventional decision game theory.

UAV imaging for spectral characterization of Coffee Leaf Miner (Leucoptera coffeella) infestation in the Cerrado Mineiro region

Abstract. Brazil, the world's largest coffee producer, faces challenges managing the coffee leaf miner (Leucoptera coffeella), a significant pest. This study suggests remote sensing for pest control decisions. Two experimental areas in the Cerrado region of Minas Gerais State were analyzed to spectrally characterize infested plants and estimate the number of mines per plant. Results show the ability to differentiate infested plants with greater reflectance variance in the near infrared at 850nm. The performances of the three machine learning algorithms were compared. Determining the number of mines in the group of most infested plants demonstrated slightly higher precision, achieving an RMSE of 22.69% using the Support Vector Machine algorithm. Conversely, the group of least-infested plants obtained the best result with the Random Forest algorithm, achieving an RMSE of 32.47%. These promising results indicated that CLM can be detected using aerial multispectral imaging data.

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%.

Advanced image processing techniques for multi-level characterization of significant flame features in carbon-neutral combustion

This research presents an advanced image processing framework designed for the multi-level characterization of significant flame features in carbon-neutral combustion systems. The study introduces an optimized neural network based on a brainstorming algorithm and an enhanced support vector machine (SVM) algorithm, which utilizes an improved particle swarm optimization (PSO) technique. The framework is capable of accurately processing complex flame image data, achieving flame classification accuracy rates of up to 100 %. The proposed system combines detailed analysis of flame brightness, texture, and morphological features, contributing to the comprehensive monitoring of combustion states. Additionally, the paper describes the design of a clean burner that promotes the full combustion of zero-carbon gases. The integration of this burner with the advanced monitoring system significantly enhances safety and efficiency in industrial applications. This work addresses the challenges associated with the transition to renewable gases and provides a robust solution for maintaining stable and efficient combustion processes.

Physicochemical characterization of thermally oxidized rapeseed oil: An insight into combining acoustic diagnostic technique and chemometrics

This study aimed to apply an ultrasonic pulse-echo system to characterize thermally oxidized rapeseed oil. After 60 h of heating treatment (165 ± 5°C), the physicochemical (density, viscosity, acid value, iodine value and polar compounds) and acoustic properties (velocity, acoustic impedance, maximum amplitude of the first echo, difference in amplitude, and area under the curve) of rapeseed oil were measured. Support vector machine, random forest (RF), and backpropagation neural network algorithms were used to establish quantitative prediction models for viscosity and polar compounds based on the acoustic properties of rapeseed oil. The results indicated significant correlations between acoustic impedance and viscosity (R=0.70), as well as between acoustic impedance and polar compounds (R=0.79). Heating treatment reduced oil unsaturation and led to the formation of oxidative and polymeric compounds, which in turn increased the velocity and impedance, while decreasing the other three acoustic features. The RF model yielded the best performance in predicting viscosity (R2=0.7944) and polar compounds (R2=0.8385). These findings highlight that ultrasonic technology not only accurately predicts key quality parameters, but also provides a rapid, non-destructive, and cost-effective alternative to traditional methods for characterizing thermally oxidized rapeseed oil.