Multiple Support Vector Machine Research Articles

Homogenous Multiple Classifier System for Software Quality Assessment Based on Support Vector Machine

In today's society, almost all human endeavours depend on software products. Lack of quality software is one of the software industry's most important problems. Hence, it would be beneficial to access the quality of software to improve and enhance software products while increasing customer satisfaction. This paper assesses software product quality using a Support Vector Machine-based ensemble classifier. The ISO/IEC-9126 (International Organization for Standardization 2001) software quality (SQ) framework was adopted in this work. Dimension reduction of the product metric category dataset and the entire PM dataset was conducted using linear discriminant analysis (LDA). SVM kernel functions (linear, quadratic, cubic, fine gaussian, medium gaussian and coarse gaussian) were used to model each classifier. The combinations of the results from the multiple SVMs used AdaBoost, bagging, and random subspace ensemble methods for the assessment of SQ. All three ensemble learning methods performed better than the individual SVM, however, the bagging stood out with an accuracy of 93.0%. Hence, it was adopted in the fusion of the SVM results and classification of SQ into classes. Results from the confusion matrix and receivers’ operating characteristics were greater than 97.99% and confirm significant improvements with an ensemble of homogenous classifiers based on SVM.

Multivariate Pattern Analysis of Lifelong Premature Ejaculation Based on Multiple Kernel Support Vector Machine.

ObjectiveThis study aimed to develop an effective support vector machine (SVM) classifier based on the multi-modal data for detecting the main brain networks involved in group separation of premature ejaculation (PE).MethodsA total of fifty-two patients with lifelong PE and 36 matched healthy controls were enrolled in this study. Structural MRI data, functional MRI data, and diffusion tensor imaging (DTI) data were used to process SPM12, DPABI4.5, and PANDA, respectively. A total of 12,735 features were reduced by the Mann–Whitney U test. The resilience nets method was further used to select features.ResultsFinally, 36 features (3 structural MRI, 7 functional MRI, and 26 DTI) were chosen in the training dataset. We got the best SVM model with an accuracy of 97.5% and an area under the curve (AUC) of 0.986 in the training dataset as well as an accuracy of 91.4% and an AUC of 0.966 in the testing dataset.ConclusionOur findings showed that the majority of the brain abnormalities for the classification was located within or across several networks. This study may contribute to the neural mechanisms of PE and provide new insights into the pathophysiology of patients with lifelong PE.

Research on the Prediction Model of the Used Car Price in View of the PSO-GRA-BP Neural Network

As the mobile Internet improves by leaps and bounds, the model of traditional offline used car trading has gradually lost the ability to live up to the needs of consumers, and online used car trading platforms have emerged as the times require. Second-hand car price assessment is the premise of second-hand car trading, and a reasonable price can reflect the objective, fair, and true nature of the second-hand car market. In order to standardize the evaluation standards of used car prices and improve the accuracy of used car price forecasts, the linear correlation between vehicle parameters, vehicle conditions, and transaction factors and used car price was comprehensively investigated, grey relational analysis was applied to filter the feature variables of factors affecting used car price, the traditional BP neural network was also optimized by combining the particle swarm optimization algorithm, and a used car price prediction method based on PSO-GRA-BPNN was proposed. The results show that only the correlation coefficient of new car price, engine power, and used car price is greater than 0.6, which has a certain linear correlation. The correlation between new car price, displacement, mileage, gearbox type, fuel consumption, and registration time on used car prices is greater than 0.7, and the impact of other indicators on used car prices is negligible. Compared with the traditional BPNN model and the multiple linear regression, random forest, and support vector machine regression models proposed by other researchers, the MAPE of the PSO-GRA-BPNN model proposed in this paper is 3.936%, which is 30.041% smaller than the error of the other three models. The MAE of the PSO-GRA-BPNN model is 0.475, which is a maximum reduction of 0.622 compared to the other three models. R can reach up to 0.998, and R2 can reach 0.984. Although the longest training time is 94.153 s, the overall prediction effect is significantly better than other used car price prediction models, providing a new idea and method for used car evaluation.

Data-driven robust optimization for cyclic scheduling of ethylene cracking furnace system under uncertainty based on kernel learning

For an ethylene cracking furnace system (ECFS), the cyclic scheduling is significant for increasing the benefit. However, the scheduling period is always more than three hundred days, the frequently changed prices of raw materials and products may lead to suboptimal results. This paper proposes a data-driven robust optimization (DDRO) approach to handle price uncertainty. The uncertainty set is constructed from historical data by the multiple kernel learning-based one-class support vector machine. With introducing the uncertainty set in the deterministic model, a tractable mixed integer nonlinear programming model is derived by the dual approach for robust optimization. An actual case study shows that the proposed approach is better hedged against uncertainties with less conservatism than the classical methods. The robust cyclic schedule obtained by the DDRO approach increases the net profit by 3.8% than the schedule generated by the deterministic model when the price system deteriorates.

Prediction of Total Soluble Solids and pH of Strawberry Fruits Using RGB, HSV and HSL Colour Spaces and Machine Learning Models.

Determination of internal qualities such as total soluble solids (TSS) and pH is a paramount concern in strawberry cultivation. Therefore, the main objective of the current study was to develop a non-destructive approach with machine learning algorithms for predicting TSS and pH of strawberries. Six hundred samples (100 samples in each ripening stage) in six ripening stages were collected randomly for measuring the biometrical characteristics, i.e., length, diameters, weight and TSS and pH values. An image of each strawberry fruit was captured for colour feature extraction using an image processing technique. Channels of each colour space (RGB, HSV and HSL) were used as input variables for developing multiple linear regression (MLR) and support vector machine regression (SVM-R) models. The result of the study indicated that SVM-R model with HSV colour space performed slightly better than MLR model for TSS and pH prediction. The HSV based SVM-R model could explain a maximum of 84.1% and 79.2% for TSS and 78.8% and 72.6% for pH of the variations in measured and predicted data in training and testing stages, respectively. Further experiments need to be conducted with different strawberry cultivars for the prediction of more internal qualities along with the improvement of model performance.

Classification of Large-Scale Datasets of Landsat-8 Satellite Image Based on LIBLINEAR Library

One of the most common machine learning approaches is linear classification. Multithreading used in LIBLINEAR Library has become an important research topic for processing large datasets. Working in a multithreaded environment accelerates the training of large datasets and increases classification accuracy. This study examines multiple linear support vector machine implementations for binary classification of Landsat-8 satellite image datasets to determine the optimal model. Four datasets have been created for different scenes in Iraq. Each dataset contains millions of pixels to be classified optimally. This article selects an appropriate algorithm for such a large dataset of current types in the LIBLINEAR library optimal for organizing large datasets using the linear SVM algorithm. Each dataset containing about 4.5 million samples was used to test the performance. The seven linear SVM techniques have statically examined the most effective SVM implementation method. Accuracy, F-Score, and Kappa are used as model assessment measures to evaluate and rank the models' performances. Based on the results, the LibLINEAR library with type 4 (LINLINEAR4) classifier was the best classifier for satellite image classification in remote sensing when applied to large datasets. The accuracy, Kappa, and f-score of the LIBLINEAR 4 classifier are as follows: (92.89 %), (73.53 %), and (77.77%) with dataset1, (96.25 %), (59.97 %), and (61.88%) with dataset2, (96.65%), (68.33%), and (70.03%), and (94.72%), (53.67%), and (56.25%), respectively, with dataset4.

Classification of Large-Scale Datasets of Landsat-8 Satellite Image Based on LIBLINEAR Library

One of the most common machine learning approaches is linear classification. Multithreading used in LIBLINEAR Library has become an important research topic for processing large datasets. Working in a multithreaded environment accelerates the training of large datasets and increases classification accuracy. This study examines multiple linear support vector machine implementations for binary classification of Landsat-8 satellite image datasets to determine the optimal model. Four datasets have been created for different scenes in Iraq. Each dataset contains millions of pixels to be classified optimally. This article selects an appropriate algorithm for such a large dataset of current types in the LIBLINEAR library optimal for organizing large datasets using the linear SVM algorithm. Each dataset containing about 4.5 million samples was used to test the performance. The seven linear SVM techniques have statically examined the most effective SVM implementation method. Accuracy, F-Score, and Kappa are used as model assessment measures to evaluate and rank the models' performances. Based on the results, the LibLINEAR library with type 4 (LINLINEAR4) classifier was the best classifier for satellite image classification in remote sensing when applied to large datasets. The accuracy, Kappa, and f-score of the LIBLINEAR 4 classifier are as follows: (92.89 %), (73.53 %), and (77.77%) with dataset1, (96.25 %), (59.97 %), and (61.88%) with dataset2, (96.65%), (68.33%), and (70.03%), and (94.72%), (53.67%), and (56.25%), respectively, with dataset4.

Control chart pattern recognition using spectral clustering technique and support vector machine under gamma distribution

Most studies on control chart patterns (CCPs) recognition assume that the measured values of process characteristic follow a normal distribution. However, by collecting large-size on-line datasets, it could be found that this assumption may not be tenable. In the present study, a method to combine spectral clustering technique with support vector machine (SVM) for recognizing CCPs under a gamma distribution, which is typically employed to represent various probability distributions, is proposed. Spectral clustering is a useful tool for segmenting the observation window to obtain the correct feature set. Multiple SVM classifiers are applied to recognize CCPs. Recognition accuracy and average run length (ARL) are indicators that are used to validate the CCP recognition ability of our proposed method. Based on the comparative studies, our proposed method in the recognition efficiency of most CCP types generally outperforms the Shewhart X¯ chart and EWMA chart with run rules. It is also noted that a more skewed underlying distribution always leads to a higher false alarm rate for our proposed method. A real-world case study of the tire manufacturing process is given to illustrate how our proposed method can be practically applied to identify and recognize the CCPs.

Development of a predictive model for university students’ core competency index using machine learning: Focusing on D University

Objectives The purpose of this study was to present implications for the development and operation of the core competency-based curriculum by predicting the core competency of college students.
 Methods The panel data of the D-CODA result panel data for the past 3 years (2019-2021) of D-University students located in the Busan area were analyzed. Machine learning prediction models such as multiple linear regression analysis (LR), random forest (RF), and support vector machine (SVM), were used to predict core competencies.
 Results The following research results were derived from the study. First, the optimal prediction model for each core competency is as follows. Professional competency was shown in the RF (random forest) model, personality competency in SVM (support vector machine), creative competency in the RF (random forest) model, challenge competency and glocal (global and local) competency in the SVM (support vector machine) model, and communication competency in the LR (multi-linear regression analysis) model. Second, in the analysis of competencies, it was found that professional competency contributes to the prediction of professional competency, and both personality competency and communication competency to that of personality competency. Third, in the model analysis to predict the overall core competency index, the optimal predictive model was found to be the RF (random forest) model which showed the least error. Fourth, in the prediction of key competency indicators in 2022, it is predicted that expertise, personality, creativity, and challenging competency will improve.
 Conclusions This study revealed that the analysis using accumulated core competency data and machine learning is useful in predicting and discriminating the core competency of college students. This study is meaningful in that it suggests the importance of periodic core competency index management at the university level and provides the basis for designing a core competency-based curriculum.

Effect of Ultrasonic Vibration in Friction Stir Welding of 2219 Aluminum Alloy: An Effective Model for Predicting Weld Strength

Friction stir welding (FSW) is today used as a premier solution for joining non-ferrous metals, although there are many limitations in its application. One of the objectives of this study was to propose an innovative welding technique, namely ultrasonic-assisted friction stir welding (UAFSW) with longitudinal ultrasonic vibration applied to the stirring head. In this paper, UAFSW mechanical properties and microstructure analysis were performed to demonstrate that the fluidity of the weld area was improved and the strengthened phase organization was partially preserved, due to the application of ultrasonic vibration. The addition of 1.8 kW of ultrasonic vibration at 1200 rpm and 150 mm/min welding parameters resulted in a 10.5% increase in the tensile strength of the weld. The ultimate tensile strength of 2219 aluminum alloy UAFSW was analyzed and predicted using mathematical modeling and machine learning techniques. A full factorial design method with multiple regression, random forest, and support vector machine was used to validate the experimental results. In predicting the tensile behavior of UAFSW joints, by comparing the evaluation metrics, such as R2, MSE, RMSE, and MAE, it was found that the RF model was 22% and 21% more accurate in the R2 metric compared to other models, and RF was considered as the best performing machine learning method.

An Analog Circuit Fault Diagnosis Approach Based on Wavelet-based Fractal Analysis and Multiple Kernel SVM

Objective: In order to diagnose the analog circuit fault correctly, an analog circuit fault diagnosis approach on basis of wavelet-based fractal analysis and multiple kernel support vector machine (MKSVM) is presented in the paper. Methods: Time responses of the circuit under different faults are measured, and then wavelet-based fractal analysis is used to process the collected time responses for the purpose of generating features for the signals. Kernel principal component analysis (KPCA) is applied to reduce the features’ dimensionality. Afterwards, features are divided into training data and testing data. MKSVM with its multiple parameters optimized by chaos particle swarm optimization (CPSO) algorithm is utilized to construct an analog circuit fault diagnosis model based on the testing data. Results: The proposed analog diagnosis approach is revealed by a four opamp biquad high-pass filter fault diagnosis simulation. Conclusion: The approach outperforms other commonly used methods in the comparisons.

Robust sex differences in functional brain connectivity are present in utero.

Sex-based differences in brain structure and function are observable throughout development and are thought to contribute to differences in behavior, cognition, and the presentation of neurodevelopmental disorders. Using multiple support vector machine (SVM) models as a data-driven approach to assess sex differences, we sought to identify regions exhibiting sex-dependent differences in functional connectivity and determine whether they were robust and sufficiently reliable to classify sex even prior to birth. To accomplish this, we used a sample of 110 human fetal resting state fMRI scans from 95 fetuses, performed between 19 and 40 gestational weeks. Functional brain connectivity patterns classified fetal sex with 73% accuracy. Across SVM models, we identified features (functional connections) that reliably differentiated fetal sex. Highly consistent predictors included connections in the somatomotor and frontal areas alongside the hippocampus, cerebellum, and basal ganglia. Moreover, high consistency features also implicated a greater magnitude of cross-region connections in females, while male weighted features were predominately within anatomically bounded regions. Our findings indicate that these differences, which have been observed later in childhood, are present and reliably detectable even before birth. These results show that sex differences arise before birth in a manner that is consistent and reliable enough to be highly identifiable.

A fusion approach to improve accuracy and estimate uncertainty in cuffless blood pressure monitoring

A substantial barrier to the clinical adoption of cuffless blood pressure (BP) monitoring techniques is the lack of unified error standards and methods of estimating measurement uncertainty. This study proposes a fusion approach to improve accuracy and estimate prediction interval (PI) as a proxy for uncertainty for cuffless blood BP monitoring. BP was estimated during activities of daily living using three model architectures: nonlinear autoregressive models with exogenous inputs, feedforward neural network models, and pulse arrival time models. Multiple one-class support vector machine (OCSVM) models were trained to cluster data in terms of the percentage of outliers. New BP estimates were then assigned to a cluster using the OCSVMs hyperplanes, and the PIs were estimated using the BP error standard deviation associated with different clusters. The OCSVM was used to estimate the PI for the three BP models. The three BP estimations from the models were fused using the covariance intersection fusion algorithm, which improved BP and PI estimates in comparison with individual model precision by up to 24%. The employed model fusion shows promise in estimating BP and PI for potential clinical uses. The PI indicates that about 71%, 64%, and 29% of the data collected from sitting, standing, and walking can result in high-quality BP estimates. Our PI estimator offers an effective uncertainty metric to quantify the quality of BP estimates and can minimize the risk of false diagnosis.

A Hybrid Model for Leaf Diseases Classification Based on the Modified Deep Transfer Learning and Ensemble Approach for Agricultural AIoT-Based Monitoring.

As possible diseases develop on plant leaves, classification is constantly hampered by obstacles such as overfitting and low accuracy. To distinguish healthy products from defective ones, the agricultural industry requires precise and error-free analysis. Deep convolutional neural networks are an efficient model of autonomous feature extraction that has been shown to be fairly effective for detection and classification tasks. However, deep convolutional neural networks often require a large amount of training data, cannot be translated, and need a number of parameters to be specified and tweaked. This paper proposes a highly effective structure that can be applied to classifying multiple leaf diseases of plants and fruits during the feature extraction step. It uses a deep transfer learning model that has been modified to serve this purpose. In summary, we use model engineering (ME) to extract features. Multiple support vector machine (SVM) models are employed to enhance feature discrimination and processing speed. The kernel parameters of the radial basis function (RBF) are determined based on the selected model in the training step. PlantVillage and UCI datasets were used to analyze six leaf image sets containing healthy and diseased leaves of apple, corn, cotton, grape, pepper, and rice. The classification process resulted in approximately 90,000 images. During the experimental implementation phase, the results show the potential of a powerful model in classification operations, which will be beneficial for a variety of future leaf disease diagnostic applications for the agricultural industry.

A winner or a loser in climate change? Modelling the past, current, and future potential distributions of a rare charophyte species

Due to human–caused eutrophication and rapid environmental changes, charophytes have become an increasingly rare component of biosphere. One of the rarest charophyte worldwide is Lychnothamnus barbatus , the only extant representative of the genus Lychnothamnus . The species occurs in Europe, Asia, Australia and North America, but the number of locations is scarce and the geographical distribution is uncertain. In this study, multiple species distribution models (SDMs: Bioclim, MaxEnt, random forest (RF) and support vector machines (SVMs)) were used to reveal the potential undiscovered locations and ranges of L. barbatus . We aimed to (1) indicate the most reliable SDM for L. barbatus ; (2) determine the most important bioclimatic factor(s) affecting this species distribution; and (3) estimate the current, past (ca. 130 ka) and future (up to 2100) habitat suitability of L. barbatus in Europe and North America. Future climate scenarios were calculated using four global climate models (GCMs): CanESM5, CNRM–CM6–1, MIROC 6, BCC-CSM2-MR and model ensemble. We documented that a SVM model, which is relatively rarely used in SDMs, performed better than commonly used MaxEnt and RF models. The most important predictors for the SVM (i.e., temperature in wettest, warmest and driest quarters; precipitation in warmest and wettest quarters) were partly different than those for MaxEnt (temperature in wettest quarter and annual temperature range). The SVM used predictors more efficiently than did MaxEnt to achieve good performance. Thus, we recommend further exploring the potential of SVMs in SDMs. Furthermore, we tested different GCMs and demonstrated that the predicted future range of Lychnothamnus is heavily dependent on the model type. Nevertheless, all the models indicated expansion of L. barbatus to other areas in Europe when the pessimistic scenario occurred. It is important for biological conservation of currently rare species—more effort could be put to conserve other, warming–vulnerable species. • As rare hydrobionts, charophytes are vulnerable to climate warming effects. • Past, present and future distribution of Lychnothamnus barbatus was modeled. • Multiple species distribution models, global climate models and scenarios were used. • This study evidenced that the rare L. barbatus may expand its range in the future. • A method to detect warming-vulnerable species among currently rare species proposed.

Thermal response time prediction-based control strategy for radiant floor heating system based on Gaussian process regression

One of the main obstacles to wider applications of radiant floor heating systems with great thermal comfort and energy efficiency is the long response time caused by large thermal inertia and little research has been conducted to effectively address this issue. In this study, an optimal control strategy based on a thermal response time prediction model for radiant floor heating systems was proposed by applying the gaussian process regression (GPR) algorithm. First, a comprehensive database of the thermal response time for various scenarios based on different building configurations, radiant floor, and weather characteristics was obtained by parametric simulations after base-case building validation. Then a sensitivity analysis of the response performance of the seven explanatory variables by Pearson correlation coefficients was conducted and a theoretical explanation was provided. Besides, the response time prediction model based on the GPR algorithm with a larger R2 of around 0.96 was obtained by an in-depth comparison with commonly used machine learning algorithms such as multiple linear regression, random forest, and support vector machines. Its accuracy was verified by cross-validation and a 25% database. Finally, an optimal control strategy based on the response time prediction model was proposed which can reduce the response time from 96 ∼ 188 mins to 44 ∼ 75 mins, achieving a reduction of 41% ∼ 64% while keeping the comparative power consumption. Therefore, the proposed optimal control strategy can effectively reduce the thermal response time of radiant floor heating systems and improve the indoor thermal comfort during the thermal response phase without sacrificing power consumption.

Early warning system for highway construction projects using GA-SVM

Construction project changes vis-a-vice their impact on the cost and time performance has been the main concern of practitioners and scholars for decades; hence, many attempts have been made to develop early warning mechanisms for decision-makers. Since many factors drive project changes, various strategies can be adopted to mitigate further alterations after awarding the contract. This study aimed at developing multiple Support Vector Machine (SVM) classifiers to enhance change prediction accuracy. 5,628 completed construction-oriented projects datasets comprising preconstruction information, obtained from the Indiana Department of Transportation (INDOT), were used to develop the models. All free kernel parameters were determined using Genetic Algorithm (GA) optimization. The results show that the models built using SVM classifiers with Radial Basis Function (RBF) kernel function were successful in decreasing the uncertainty associated with change order occurrence in the early phases of the projects. Therefore, the study recommends that agencies, developers, and contractors store historical project data to build early warning systems using machine learning techniques.

OccupancySense: Context-based indoor occupancy detection & prediction using CatBoost model

Occupancy detection and prediction are two well-established problems which can be improved further to achieve higher accuracy in both cases than the existing solutions. To achieve the desired higher accuracy, proposed OccupancySense model detects human presence and predicts indoor occupancy count by the fusion of Internet of Things (IoT) based indoor air quality (IAQ) data along with static and dynamic context data which is a unique approach in this domain. This data fusion helps us to achieve higher forecasting accuracy along with the integration of state of the art gradient boosting based categorical features supported CatBoost algorithm. For comparison, other commonly used machine learning classification and regression algorithms, e.g., Multiple Linear Regression (MLR), Decision Tree (DT), Random Forests (RF) and Support Vector Machine (SVM) for regression and Logistic Regression (LR), Naïve Bayes (NB), Decision Tree (DT) and Random Forest (RF), Support Vector Machine (SVM) for classification, were also assessed during this experiment. Out of these, CatBoost outperformed other models when considered in terms of accuracy. Hence, CatBoost is used as the core of the OccupancySense design and we have validated the proposed model by a real-world case study with continuous 91 days of indoor data, having 33 unique external features. These features are collected directly as well as derived from the collected data. To handle these features, feature engineering plays a key role in the OccupancySense model. The speciality of this model is, it is non-intrusive one but have high predictive power. It can detect occupancy and predicts headcount along with occupancy density of the room pretty accurately with 99.85%, 93.2% and 95.6% respectively (with 10 fold cross-validation) which outperforms other state of the art models.

Novel quantitative structure activity relationship models for predicting hexadecane/air partition coefficients of organic compounds

Predicting the logarithm of hexadecane/air partition coefficient (L) for organic compounds is crucial for understanding the environmental behavior and fate of organic compounds and developing prediction models with polyparameter linear free energy relationships. Herein, two quantitative structure activity relationship (QSAR) models were developed with 1272 L values for the organic compounds by using multiple linear regression (MLR) and support vector machine (SVM) algorithms. On the basis of the OECD principles, the goodness of fit, robustness and predictive ability for the developed models were evaluated. The SVM model was first developed, and the predictive capability for the SVM model is slightly better than that for the MLR model. The applicability domain (AD) of these two models has been extended to include more kinds of emerging pollutants, i.e., oraganosilicon compounds. The developed QSAR models can be used for predicting L values of various organic compounds. The van der Waals interactions between the organic compound and the hexadecane have a significant effect on the L value of the compound. These in silico models developed in current study can provide an alternative to experimental method for high-throughput obtaining L values of organic compounds.

Identification of Diagnostic Biomarkers Associated with Stromal and Immune Cell Infiltration in Fatty Infiltration After Rotator Cuff Tear by Integrating Bioinformatic Analysis and Machine-Learning.

PurposeThe present study aimed to explore potential diagnostic biomarkers for fatty infiltration (FI) of the rotator cuff muscles after rotator cuff tear (RCT) and investigate the influence of stromal and immune cell infiltration on this pathology.MethodsThe GSE130447 and GSE103266 datasets were downloaded from the Gene Expression Omnibus database. Differentially expressed genes (DEGs) were identified, and gene set enrichment analyses were performed by R software. Two machine learning algorithms, random forest and multiple support vector machine recursive feature elimination (mSVM-RFE), were used to screen candidate biomarkers. The diagnostic value of the screened biomarkers was further validated by the area under the ROC curve (AUC) in the GSE103266 dataset. Murine microenvironment cell population counter (mMCP-counter) method was employed to estimate stromal and immune cell infiltration of FI. The correlation between biomarkers and infiltrated immune and stromal cell subsets was further analyzed.ResultsA total of 2123 DEGs were identified. The identified DEGs were predominantly linked to immune system process, extracellular matrix organization and PPAR signalling pathway. FABP5 (AUC = 0.958) and MGP (AUC = 1) were screened as diagnostic biomarkers of FI. Stromal and immune cell infiltration analysis showed that monocytes, mast cells, vessels, endothelial cells and fibroblasts may be related to the process of FI. FABP5 and MGP were positively correlated with vessels whereas negatively correlated with monocytes and mast cells.ConclusionFABP5 and MGP can serve as diagnostic biomarkers of FI after RCT, and stromal and immune cell infiltration may play a crucial role in this pathology.