Correlation Of Features Research Articles

DeepAge: Harnessing Deep Neural Network for Epigenetic Age Estimation From DNA Methylation Data of Human Blood Samples

Accurate prediction of biological age from DNA methylation data is a critical endeavor in understanding the molecular mechanisms of aging and developing age-related disease interventions. Traditional epigenetic clocks rely on linear regression or basic machine learning models, which often fail to capture the complex, non-linear interactions within methylation data. This study introduces DeepAge, a novel deep learning framework utilizing Temporal Convolutional Networks (TCNs) to enhance the prediction of biological age from DNA methylation profiles using selected CpGs by a Dual-Correlation based apparoach. DeepAge leverages a sequence-based approach with dilated convolutions to effectively capture long-range dependencies between CpG sites, addressing the limitations of prior models by incorporating advanced network architectures including residual connections and dropout regularization. The dual correlation feature selection enhances our model's predictive capabilities by identifying the most age-relevant CpG sites. Our model outperforms existing epigenetic clocks across multiple datasets, offering significant improvements in accuracy and providing deeper insights into the epigenetic determinants of aging. The proposed method not only sets a new standard in age estimation but also highlights the potential of deep learning in biologically relevant feature extraction and interpretation, contributing to the broader field of computational biology and precision medicine.

METAHEURISTIC-ASSISTED HYBRID RECOGNITION MODEL FOR BRAIN ACTIVITY DETECTION

Electroencephalogram (EEG) recordings typically capture the integrals of active brain potentials, which vary in latencies and populations. Anomalies in EEG data, often associated with epilepsy, play a crucial role in identifying conditions such as brain death, encephalopathy, coma, depth of anesthesia, and sleep disturbances. To get early warnings for these diseases, this work intends to propose a novel approach for brain activity detection from EEG signals. A new Hybrid Classification of Combined Coot Blue Monkey Optimization (HC-CCBO) method is proposed in this work. Initially, improved [Formula: see text]-score normalization was used to preprocess the EEG signal. Further, Discrete Wavelet Transform (DWT), improved correlation and statistical features were extracted. After that, we set up hybrid classification, which exploited Bi-Directional Gated Recurrent Unit (Bi-GRU) and Deep Max Out (DMO) models. Further, weights of BI-GRU and DMO were optimized via Combined Coot Blue Monkey Optimization (CCBO) optimization. Finally, we obtain the output scores of the rest, left fist, both fists, right fist, and both feet from the suggested hybrid brain activity recognition model. The effectiveness of the suggested HC-CCBO model is compared to conventional techniques using a variety of metrics. Compared to the existing models, the suggested model obtains a high maximum accuracy of 0.93 at the 90th learning percentage.

A two-dimensional magnetotelluric deep learning inversion approach based on improved Dense Convolutional Network

Magnetotelluric (MT) inversion is an important means of MT data interpretation. The use of deep learning technology for MT inversion has attracted much attention because it is not limited to the initial model, avoids falling into local optimal solutions, and has the strong ability to process large amounts of data. However, obtaining highly reliable deep learning inversion results remains a challenge. In this paper, we have proposed a two-dimensional (2-D) MT inversion method based on the improved Dense Convolutional Network (DenseNet), with the aim of improving the reliability of the 2-D deep learning MT inversion results. First, the MARE2DEM is used to compute the 2-D MT forward responses when establishing the sample set. Then, an improved DenseNet is proposed by incorporating depthwise separable convolution in lieu of standard convolution within dense connection blocks, and embedding the attention mechanism. Depthwise separable convolution splits the standard convolution operation into depthwise and pointwise convolution, effectively capturing spatial features of input data and correlations between channels. Meanwhile, attention mechanism allows the network to assign varying degrees of importance (or attention) to different elements in a sequence of data, thus enhancing its ability of key feature extraction. This design not only retains the inherent feature reuse and alleviates gradient vanishing of DenseNet but also further enhances network performance. The optimized network parameters for the improved DenseNet are obtained by training on the training set, while the validation set is used to adjust hyperparameters and evaluate model performance. Finally, the proposed 2-D deep learning approach is verified by using both synthetic and field data. Experimental results with synthetic data show that the reliability of inversion results obtained by using the proposed algorithm is improved, and the inversion results obtained by using both TE- and TM-mode data is more accurate than those obtained by using the single mode data. The inversion results of field data show that the proposed 2-D MT deep learning inversion approach can effectively detect the subsurface resistivity structure and has a good application prospect.

Diagnosing Fungal Infection in Wheat Kernels by Integrating Spectroscopic Technology and Digital Color Imaging System: Artificial Neural Network, Principal Component Analysis and Correlation Feature Selection Techniques

ABSTRACTContamination of cereal grain, especially wheat, with fungal infections can cause significant economic impacts and it endangers the health of humans and livestock. This study aims to appraise the UV/VIS–NIR and digital color (RGB) imaging systems and spectroscopic methodology to detect wheat kernels infected by fungi such as Penicillium expansum and Fusarium graminearum. NIR spectra of 190–1100 nm at 10 nm intervals, visible color reflectance images and non‐visible reflectance images of wheat kernels in the ultraviolet and near‐infrared ranges were applied to develop the multi‐layer perceptron (MLP) artificial neural network model. The optimum wavelengths were selected by application of the principal component analysis (PCA) after preprocessing the raw spectra. A confusion matrix was used in the correlation feature selection method (CFS) for the decision tree classifier of selected features. The results showed that the four UV wavelengths of 310, 330, 400, and 410 nm were the best wavelengths using PCA to distinguish healthy and unhealthy wheat kernels. Considering the intensity of the wavelengths as the neural network inputs, samples were classified into healthy and unhealthy categories with an accuracy of 90.9%. Also, 18 features of color images in RGB, LAB, HSV, HSI, YCbCr, and YIQ spaces provided the highest average accuracy of 44.4% in classifying healthy and infected wheat kernels by using a CCD Proline camera in the ultraviolet range. In contrast, other cameras in the visible and invisible range showed low accuracy. Furthermore, the best classification accuracy of the healthy and infected samples by the use of the CFS method was obtained at 88.1%. Based on the findings, spectroscopic methodology proved to be highly effective for detecting, classifying and automatic cleaning of various agricultural seeds, with a particular emphasis on wheat kernals.

Road Pothole Detection Model Based on Local Attention Resnet18-CNN-LSTM

Abstract. In response to the low detection accuracy and slow speed of existing road pothole detection methods, a road pothole classification detection model based on local attention Resnet18-CNN-LSTM (Long Short-Term Memory network) is proposed. On the basis of Resnet18, a local attention mechanism and a CNN-LSTM combined model are added to propose a road pothole detection model based on local attention Resnet18-CNN-LSTM. The local attention mechanism is used to accurately extract specific target feature values, CNN is used to extract the spatial features of the input data, and LSTM enhances the detection model's extraction of sequential features and performs classification, thereby improving the accuracy of the road and pothole model. Experimental results show that on the training set, the accuracy of the local attention mechanism-based ResNet18-CNN-LSTM model reached 99.2188%, which is an increase of 0.7813% and 2.3438% compared to the ResNet34-CNN-LSTM and ResNet50-CNN-LSTM models under the same conditions, respectively. On the test set, the model's accuracy was 93.4437%, an increase of 0.5437% and 1.9867% compared to the ResNet34-CNN-LSTM and ResNet50-CNN-LSTM models, respectively. After dealing with overfitting issues through early stopping, the detection accuracy of this model has significantly improved compared to the detection models based on ResNet34 and ResNet50, with an increase of 1.2% and 1.49% respectively. The model shows faster processing speed in identification time, effectively retains the correlation and sequence features of the data, overcomes the problem of gradient disappearance in deep networks, and thereby enhances the extraction capability of local target features of road pothole images. The above results indicate that the local attention mechanism-based ResNet18-CNN-LSTM model shows superior performance in road pothole detection.

Reproducibility and interpretability in radiomics: a critical assessment.

Radiomics aims to improve clinical decision making through the use of radiological imaging. However, the field is challenged by reproducibility issues due to variability in imaging and subsequent statistical analysis, which particularly affects the interpretability of the model. In fact, radiomics extracts many highly correlated features that, combined with the small sample sizes often found in radiomics studies, result in high-dimensional datasets. These datasets, which are characterized by containing more features than samples, have different statistical properties than other datasets, thereby complicating their training by machine learning and deep learning methods. This review critically examines the challenges of both reproducibility issues and interpretability, beginning with an overview of the radiomics pipeline, followed by a discussion of the imaging and statistical reproducibility issues. It further highlights how limited model interpretability hinders clinical translation. The discussion concludes that these challenges could be mitigated by following best practices and by creating large, representative, and publicly available datasets.

Deep spatial-temporal information fusion dynamic graph convolutional network for traffic flow prediction

Abstract Predicting traffic flow is vital for advancing intelligent transportation systems, but achieving precise forecasts remains challenging. To deeply explore the complex and diverse dynamic spatio-temporal correlation of traffic data, this study proposes a multi-information fusion spatio-temporal dynamic graph convolution model for traffic flow prediction. In the model construction, firstly, a dynamic graph generation module is designed to fully capture the complex spatial correlation of the traffic network and model the changing spatio-temporal interaction; secondly, the spatial self-attention mechanism is used to dynamically focus on the spatial relationship between different nodes, and combined with the dynamic graph convolution network to extract the spatial dynamic correlation features of the road network to study deep spatiotemporal information; Finally, existing models rarely consider other traffic information related to traffic flow, and a spatiotemporal information fusion module is designed to enhance the ability of the model to perceive information, thereby improving the performance of traffic flow prediction models. Experiments are conducted on four real traffic datasets using three performance evaluation metrics and 18 baseline models. The results show that the model has higher prediction accuracy.

Principles and prospects of Bose-Einstein correlation study at BESIII* *This study was supported by the National Key R&D Program of China (2020YFA0406403) and the National Natural Science Foundation of China (11275211, 11335008, 12035013)

One method for determining the characteristic parameters of a hadron production source is to measure the Bose-Einstein correlation functions. In this study, we present fundamental concepts and formulas related to the Bose-Einstein correlations, focusing on the measurement principles and the Lund model from an experimental perspective. We perform Monte Carlo simulations using the Lund model generator in the 2–3 GeV energy range. Through these feasibility studies, we identify key features of the Bose-Einstein correlations that offer valuable insights for experimental measurements. Utilizing data samples collected at BESIII, we perform measurements of the Bose-Einstein correlation functions, with an expected experimental precision of a few percent for the hadron source radius and incoherence parameter.

Investigation of age-hardening behaviour of Al alloys via feature screening-assisted machine learning

Age hardening stands as a crucial strengthening process for aluminium (Al) alloys. However, determining the optimal ageing conditions has traditionally relied on resource-intensive trial-and-error methods. To streamline the design of Al alloys, this study introduces a novel feature screening-assisted machine learning (ML) approach to explore age-hardening behaviour across varying compositions and heat treatment parameters, focusing on yield tensile strength (YTS), ultimate tensile strength (UTS), and elongation (EL). A comprehensive pool of features, incorporating alloy composition and fundamental elemental properties, was generated to provide metallurgical insights for ML predictions. Subsequently, feature screening methodologies, including correlation analysis, feature elimination, and multi-objective genetic algorithm (MOGA), were employed to identify key features from the vast feature pool, balancing model complexity and prediction accuracy. Employing support vector regression models trained on these optimized feature sets, we demonstrate enhanced prediction accuracy for strength properties while maintaining model simplicity for EL, with minimal impact on accuracy. In addition, experimental results further validate the method's ability to reproduce ageing curves across all three mechanical properties for both commercialized and newly designed Al alloys.

Dynamic Multi-Factor Correlation Analysis for Prediction of Provincial Carbon Emissions in China’s Bohai Rim Region

This study presents a dynamic multi-factor correlation analysis method designed to predict provincial carbon dioxide emissions (CDE) within China’s Bohai Rim region, including Tianjin, Hebei, Shandong, and Liaoning. By employing the sliding window technique, dynamic correlation curves are computed between various influencing factors and CDE at different time intervals, thereby facilitating the identification of key feature attributes. A novel metric, the Consistency Index of Influencing Factors (CIIF), is introduced to evaluate the consistency of these factors across regions. Furthermore, the Accurate Predictive Capability Indicator (APCI) is defined to measure the impact of different feature categories on the prediction accuracy. The findings reveal that models relying on a single influencing factor exhibit limited accuracy, whereas combining multiple factors with diverse correlation features significantly improves the prediction accuracy. This study introduces a refined analytical framework and a comprehensive indicator system for CDE prediction. It enhances the understanding of the complex factors that influence CDE and provides a scientific rationale for implementing effective emission reduction strategies.

Feature correlation fusion and feature selection under adaptive neighborhood group approximation space

Feature correlation fusion and feature selection under adaptive neighborhood group approximation space

Enhanced intrusion detection framework for securing IoT network using principal component analysis and CNN

ABSTRACT The Internet of Things (IoT) has transformed our world by connecting smart devices and enabling seamless interactions. This reliance, however, has led to new security issues and types of attacks. It is of the utmost importance to safeguard the security of IoT networks, with network intrusion detection systems (NIDS) having a significant impact. This paper proposes a novel approach integrating Principal Component Analysis (PCA), Pearson Correlation Coefficient (PCC), and Convolutional Neural Network (CNN) to overcome these security issues. Our innovative method reduces data dimensionality and selects highly correlated features using PCC and PCA, addressing overfitting and improving model performance while maintaining high computational speed and low costs. Our approach uniquely distinguishes between benign and threat packets by employing 1D-CNN, 2D-CNN, and 3D-CNN algorithms trained on Edge-IIoTset and NSL-KDD benchmark datasets. The findings from our experiments indicate that the proposed framework significantly enhances accuracy, precision, recall, and F1-score compared to existing models for both binary and multiclass classifications. Our binary classification models achieved exceptional performance, with an average accuracy of 99.76%, 99.79% precision, 99.89% recall, and 99.85% F1-score on the Edge-IIoTset dataset. On the NSL-KDD dataset, the models attained 99.20% accuracy, 98.07% precision, 97.95% recall, and 97.71% F1-score. For multiclass classification, the proposed model demonstrated an average accuracy of 99.41%, precision of 98.61%, recall of 98.49%, and an F1-score of 98.56% on the Edge-IIoTset dataset. On the NSL-KDD dataset, the model achieved 92.43% accuracy, 93.21% precision, 93.60% recall, and a 93.7% F1-score. Our research introduces a significant advancement that substantially improves NIDS capabilities, making IoT networks safer and more connected.

Optimization of the age of correlated information in V2X networks with edge computing

Vehicle-to-Everything (V2X) communication has the potential to revolutionize the travel experience in intelligent transportation, which has received the great attention recently. However, ensuring the freshness of information from multiple sources is critical for the real-time and reliable communication in vehicular networks, especially for timely updates of service centers. To address this issue, we use a promising metric called Age of Correlated Information (AoCI), which can characterize the freshness of multi-source information. Therefore, we propose a novel model that can dynamically regulate the channel activation matching and edge computing collaboration strategy to minimize AoCI in V2X vehicular networks. Firstly, we describe the system model of a V2X network with edge computing, including definitions and assumptions for freshness of information, edge co-computing, etc. Secondly, we formulate the joint optimization problem as a source-related age minimization (SRAM) problem, which is NP-complete. A heuristic algorithm is proposed to solve it under fast-fading channel. Finally, since traditional graph models cannot capture the changing correlation between nodes in dynamic networks, we use graph convolutional networks(GCN) to extract the features of multi-source correlation. The features extracted by GCN include relevant attributes of the sources and its communication links. The features are provided as input to a double deep Q network (DDQN) for training the model that can adapt to a dynamic network environment. Extensive simulation experiments in different network scenarios validate that our proposed method can effectively and efficiently reduce the average AoCI and the computational resources.

HYBRID ARCHITECTURE WITH IMPROVED SCORE LEVEL FUSION FOR PATIENT WAITING TIME PREDICTION

Hospitals are overcrowded in proportion to the massive increase in population, making it difficult for hospitals to manage or arrange or shorten patient wait time during medical care. However, it is difficult to overstate the significance of patient waiting time management and predictability. In most of the hospitals, the clinical workflow is defined and driven by the patient queues. Predicting the incoming patients and waiting times has thus emerged as one of the most crucial clinical management techniques. Our proposed work aims to address the limitations of current waiting time prediction models by providing a more sophisticated, data-driven approach that can adapt to the complexities of healthcare environments. This work focuses on developing a new model for predicting the patient’s waiting time. The primary aim of this research is to create a reliable predictive model capable of accurately anticipating patient waiting times. This innovation aims to enhance both patient satisfaction and operational efficiency within healthcare settings. By offering healthcare administrators a tool to better manage patient flow, allocate resources efficiently, and minimize waiting times, this model seeks to optimize overall healthcare service delivery. The initial process carried out is pre-processing which includes data acquisition and improved [Formula: see text]-score normalization. Subsequently, entropy features, correlation features, and improved mutual information (MI) features are extracted. Then, prediction is carried out using hybrid classifier (HC) that involves a convolutional neural network (CNN) and bidirectional gated recurrent unit (Bi-GRU). Finally, improved score level fusion (ISLF) is introduced to get absolute outcomes on WTP. The analysis outcomes on varied error metrics show the efficacy of the proposed WTP model.

On the prediction and optimization of the flow boiling heat transfer in mini and micro channel heat sinks

The most common methods for predicting flow boiling heat transfer in mini/micro channels-based heat sinks rely on semi-empirical correlations derived from experimental data. However, these correlations are often limited to specific testing conditions. This study proposes a novel approach using deep learning and genetic algorithms (GA) to predict and optimize refrigerants' flow boiling heat transfer coefficients (FBHTC) in mini/microchannels-based heat sinks. The dataset used in this study includes FBHTC observations from the literature for seven refrigerants (R1234yf, R1234ze, R134A, R513A, R410A, R22, and R32). The optimal input parameters identified include hydraulic diameters ranging from 1 to 7 mm, saturation temperature from 0 to 20 °C, flow qualities from 0.006 to 0.972, heat flux from 3 to 78.8 kW/m2, and mass fluxes between 100 and 1200 kg/m2s. Gradient-boost regression trees were employed to develop the deep learning and GA models for accurate estimation and optimization. Correlation analysis and feature engineering selected the most influential parameters to construct a precise and simple model. The results demonstrate that the models could estimate refrigerants' FBHTC with high accuracy, achieving an R2 of 0.988 and a mean squared error (MSE) of 0.05%. The GA-based method effectively optimized the FBHTC for each refrigerant by determining the appropriate input parameters, including the saturation temperature, heat and mass fluxes, quality, and hydraulic diameter. Additionally, a parametric analysis using explainable artificial intelligence was conducted to interpret the impact of each input parameter on the FBHTC.

State-of-health estimation for lithium-ion batteries using relaxation voltage under dynamic conditions

The data-driven approach accurately estimates the state-of-health of lithium-ion batteries using online data, aiding consumers in operational and maintenance decisions. However, the stochastic charging and discharging behavior in realistic scenarios leads to continuous transient processes that render conventional features undetectable or exacerbate fluctuations. Here, we use domain knowledge and equivalent circuit modeling to investigate the extraction of physical features of aging through a relatively stable relaxation process under dynamic conditions. Our study uses 16-cell data from the National Aeronautics and Space Administration randomized dataset and compares four basic data-driven models for validation. The results show that incorporating a limited set of previous discharge step information significantly enhances model robustness and accuracy. The best-performing model, auto-relevance determination gaussian process regression, achieves a low root mean square error of 1.94 %. Physically interpretable features do not rely on historical data, require a smaller sample size, and exhibit greater generalizability across different current scenarios. This method does not depend on a specific charging method, making it practical and adaptable. Therefore, the data-driven approach utilizing relaxation voltages and correlation features offers a viable solution for accurately estimating the health state of lithium-ion batteries under dynamic conditions.

Light field images super-resolution method based on hybrid low-dimensional spatial–angular interaction feature and linear complementation epipolar feature

Light-field (LF) cameras record 4D information about the intensity and angle of light, but limited by the resolution of the sensor, LF images require a trade-off between spatial and angular resolution, which results in generally low spatial resolution for LF images. We work on spatial super-resolution reconstruction (SR) of LF images, but due to the high dimensionality of 4D LF, it is difficult to process it directly, so we decompose 4D LF into low-dimensional sub-spaces. Since the 4D features of interest to different low-dimensional sub-spaces are different, we design a hybrid network structure—HSAESR, which processes multiple low-dimensional sub-spaces individually to adequately model the texture information in the 4D LF. HSAESR is designed to reconstruct Macro Pixel Images (MacPI) and Extremely Planar Images (EPI) respectively, and the final reconstruction results are weighted and fused. For MacPI, a CNN-based feature interaction module is designed using a novel asymptotic ’grid’ interaction approach to fully utilize the correlation between the 2D spatial dimension and the 2D angular dimension sub-spaces in 4D LF. For EPI, a Transformer-based epipolar feature linear complementation module is designed learning global and non-global multi-directional epipolar feature correlations, which learns feature linear correlation factor (α) and linear bias weight (β) through the correlation of non-global epipolar features, and corrects and complements the global epipolar correlation features through feature linear complementation. Extensive experiments are conducted on five datasets, the results show that HSAESR further improves the performance of LF images spatial SR, the reconstruction results are better than the comparison methods.

Bone-A-Fide Breakthrough: Machine Learning Cracks the Code on Osteoporosis Treatment Using the Irish Hip Fracture Database

Abstract Background Osteoporosis is a metabolic bone disorder characterised by decreased bone mineral density and mass. Due to its asymptomatic nature, it often remains undiagnosed and untreated until a fracture occurs. Traditionally, treatment decisions for osteoporosis are based on clinical appropriateness while balancing the treatment's risks and benefits. Machine learning (ML) is revolutionising healthcare domains through pattern recognition of previously “unseen” observations. Presently, its application in osteoporosis is limited to early diagnosis. More research is needed to examine its role in guiding osteoporosis treatment. This study aims to identify new predictive attributes for osteoporosis treatment using ML techniques on data from the Irish Hip Fracture Database (IHFD). Methods Datasets from January to March 2023 in University Hospital Waterford were sourced from the IHFD. Osteoporosis treatment decisions were obtained from discharge letters. Preliminary data cleaning was performed in Excel with zero-variance and near-zero predictor. Attributes excluded. The dataset was entered into the WEKA 3.8.6 environment for ML processing. Results The initial dataset containing 141 instances and 32 attributes was refined using the Correlation Feature Selection and Ranker Search Method, identifying key osteoporosis treatment predictors. The highest correlation attributes are pre-fracture total score, pre-fracture indoor score, and age. Moderately positive correlations are discharge destination, pre-fracture outdoor and shopping score, ASA grade, Length-of-stay, admission code, Admission 4AT score, Frailty scale, and fracture type. The implemented J48 Tree ML-trained model revealed Correctly Classified Instances and Incorrectly Classified Instances of 98.24% and 1.7%, respectively, indicating a high prediction accuracy rate. Conclusion This study demonstrates the potential of ML in enhancing osteoporosis treatment decision-making by leveraging datasets from the IHFD. Integrating ML algorithms with traditional approaches can provide a comprehensive, nuanced and personal approach to osteoporosis treatment and patient care. The study opens avenues for future research in applying big data and advanced analytics in healthcare, underscoring the evolving landscape of medical decision-making.

Development and optimization of an Artificial Neural Network (ANN) model for predicting the cadmium fixation efficiency of biochar in soil

This study addresses the issue of soil cadmium pollution and the common problem of data missing during the training of artificial neural network models. A substantial amount of characteristic data regarding the immobilization of cadmium in soil through biochar was collected from the literature. Subsequently, data was organized and analyzed using correlation matrix analysis and feature importance analysis. The results revealed that the feature importance of biochar (52%) was relatively significant. A novel approach is introduced, involving a non-deterministic optimization technique based on linear interpolation to supplement the missing data within the dataset. The completed dataset effectively preserves the distributional characteristics of the original data, thereby enhancing the training performance of the neural network model. Through three phases, namely data incompleteness, data supplementation, and genetic algorithm optimization, the neural network model was progressively refined. The outcome of this iterative process is a high-performance artificial neural network model capable of predicting the efficiency of biochar in immobilizing cadmium in soil. The significance of these findings lies in their potential to advance the application of machine learning in environmental science, particularly in addressing complex pollution scenarios.

Machine Learning-Driven GCC Loop Unrolling Optimization: Compiler Performance Enhancement Strategy Based on XGBoost

In contemporary compilers, the determination of the loop unrolling factor is traditionally based on manually crafted heuristic rules. This approach heavily relies on human intuition, which limits its ability to achieve optimized performance across diverse architectures and can sometimes even lead to performance declines. Additionally, developers face challenges in achieving cross-platform compatibility, often necessitating extensive redesign efforts. In response, this study introduces a method leveraging the XGBoost algorithm to predict the optimal loop unrolling factor for compiler optimization, thereby aiming to replace human thinking with machine learning methods and standardize development processes. Initially, the study gathers data on the loop unrolling factors as determined by profile guided optimization technology, analyzes program-specific loop feature vectors and employs cross-validation, including the Pearson correlation coefficient and feature importance ranking, to construct a dataset. Subsequent use of XGBoost to train this dataset models the decision-making process for selecting the most effective loop unrolling factor. The final step involves integrating XGBoost’s trained decision tree model into GCC to calculate the optimal loop unrolling factor during actual compilation. Empirical results on the RISC-V platform indicate that this new method, when tested against the SPEC CPU 2006 benchmark suite, offers up to 6.18% improvement in performance over the existing heuristic approach. It provides a new method for loop unrolling in compilers, and provides an innovative guide for the application of machine learning in compilers.