ML Methods Research Articles

Development and validation of a machine learning-based nomogram for predicting HLA-B27 expression

BackgroundHLA-B27 positivity is normal in patients undergoing rheumatic diseases. The diagnosis of many diseases requires an HLA-B27 examination.MethodsThis study screened totally 1503 patients who underwent HLA-B27 examination, liver/kidney function tests, and complete blood routine examination in First Affiliated Hospital of Guangxi Medical University. The training cohort included 509 cases with HLA-B27 positivity whereas 611 with HLA-B27 negativity. In addition, validation cohort included 147 cases with HLA-B27 positivity whereas 236 with HLA-B27 negativity. In this study, 3 ML approaches, namely, LASSO, support vector machine (SVM) recursive feature elimination and random forest, were adopted for screening feature variables. Subsequently, to acquire the prediction model, the intersection was selected. Finally, differences among 148 cases with HLA-B27 positivity and negativity suffering from ankylosing spondylitis (AS) were investigated.ResultsSix factors, namely red blood cell count, human major compatibility complex, mean platelet volume, albumin/globulin ratio (ALB/GLB), prealbumin, and bicarbonate radical, were chosen with the aim of constructing the diagnostic nomogram using ML methods. For training queue, nomogram curve exhibited the value of area under the curve (AUC) of 0.8254496, and C-value of the model was 0.825. Moreover, nomogram C-value of the validation queue was 0.853, and the AUC value was 0.852675. Furthermore, a significant decrease in the ALB/GLB was noted among cases with HLA-B27 positivity and AS cases.ConclusionTo conclude, the proposed ML model can effectively predict HLA-B27 and help doctors in the diagnosis of various immune diseases.

Sharpen data-driven prediction rules of individual large earthquakes with aid of Fourier and Gauss

Predicting individual large earthquakes (EQs)’ locations, magnitudes, and timing remains unreachable. The author’s prior study shows that individual large EQs have unique signatures obtained from multi-layered data transformations. Via spatio-temporal convolutions, decades-long EQ catalog data are transformed into pseudo-physics quantities (e.g., energy, power, vorticity, and Laplacian), which turn into surface-like information via Gauss curvatures. Using these new features, a rule-learning machine learning approach unravels promising prediction rules. This paper suggests further data transformation via Fourier transformation (FT). Results show that FT-based new feature can help sharpen the prediction rules. Feasibility tests of large EQs (Mge 6.5) over the past 40 years in the western U.S. show promise, shedding light on data-driven prediction of individual large EQs. The handshake among ML methods, Fourier, and Gauss may help answer the long-standing enigma of seismogenesis.

Toward assessment of human voice biomarkers of brain lesions through explainable deep learning

Lesions in the brain resulting from traumatic injuries or strokes can evolve into speech dysfunction in undiagnosed patients. Employing ML-based tools to analyze the prosody or articulatory phonetics of human speech could be advantageous for early screening of undetected brain injuries. Additionally, explaining the model’s decision-making process can support predictions and take appropriate measures to improve patient voice quality. However, traditional ML methods relying on low-level descriptors (LLDs) may sacrifice detailed temporal dynamics and other speech characteristics. Interpreting these descriptors can also be challenging, requiring significant effort to understand feature relationships and suitable ranges. To address these limitations, this research paper introduces xDMFCCs, a method that identifies interpretive discriminatory acoustic biomarkers from a single speech utterance, providing local and global interpretations of deep learning models in speech applications. To validate this approach, it was implemented to interpret a Convolutional Neural Network (CNN) trained on Mel-frequency Cepstral Coefficients (MFCC) for the binary classification task to differentiate between patients from control vocalizations. The ConvNet achieved promising results with a 75% f-score (75% recall, 76% precision), comparable to conventional machine learning baselines. What sets xDMFCCs apart is its explanation through a 2D time–frequency representation that preserves the complete speech signal. This representation offers a more transparent explanation for differentiating between patients and healthy controls, enhancing interpretability. This advancement enables more detailed and compelling studies in speech acoustic traits of brain lesions. Furthermore, the findings have significant implications for developing low-cost and rapid diagnostics of unnoticed brain lesions.

A Machine Learning-Based Method for Detecting Liver Fibrosis.

Cholecystectomy and Metabolic-associated steatotic liver disease (MASLD) are prevalent conditions in gastroenterology, frequently co-occurring in clinical practice. Cholecystectomy has been shown to have metabolic consequences, sharing similar pathological mechanisms with MASLD. A database of MASLD patients who underwent cholecystectomy was analysed. This study aimed to develop a tool to identify the risk of liver fibrosis after cholecystectomy. For this purpose, the extreme gradient boosting (XGB) algorithm was used to construct an effective predictive model. The factors associated with a better predictive method were platelet level, followed by dyslipidaemia and type-2 diabetes (T2DM). Compared to other ML methods, our proposed method, XGB, achieved higher accuracy values. The XGB method had the highest balanced accuracy (93.16%). XGB outperformed KNN in accuracy (93.16% vs. 84.45%) and AUC (0.92 vs. 0.84). These results demonstrate that the proposed XGB method can be used as an automatic diagnostic aid for MASLD patients based on machine-learning techniques.

Dynamic Power Management in Large Manycore Systems: A Learning-to-Search Framework

The complexity of manycore System-on-chips (SoCs) is growing faster than our ability to manage them to reduce the overall energy consumption. Further, as SoC design moves toward three-dimensional (3D) architectures, the core's power density increases leading to unacceptable high peak chip temperatures. In this article, we consider the optimization problem of dynamic power management (DPM) in manycore SoCs for an allowable performance penalty (say, 5%) and admissible peak chip temperature. We employ a machine learning– (ML) based DPM policy, which selects the voltage/frequency levels for different cluster of cores as a function of the application workload features such as core computation and inter-core traffic, and so on. We propose a novel learning-to-search (L2S) framework to automatically identify an optimized sequence of DPM decisions from a large combinatorial space for joint energy-thermal optimization for one or more given applications. The optimized DPM decisions are given to a supervised learning algorithm to train a DPM policy, which mimics the corresponding decision-making behavior. Our experiments on two different manycore architectures designed using wireless interconnect and monolithic 3D demonstrate that principles behind the L2S framework are applicable for more than one configuration. Moreover, L2S-based DPM policies achieve up to 30% energy-delay product savings and reduce the peak chip temperature by up to 17 °C compared to the state-of-the-art ML methods for an allowable performance overhead of only 5%.

Modelling the interface bond strength of corroded reinforced concrete using hybrid machine learning algorithms

The mechanical properties of corroded reinforced concrete are intricately associated with bond strength between corroded reinforcement and concrete. This strength must be predicted with ease and precision in practical engineering settings. This research proposes a prediction model for the bond strength of corroded reinforced concrete based on a hybrid machine learning algorithm using SHAP values. The model is based on ML algorithms, such as SVM, RF, and XGB, and is constructed based on 166 sets of experimental research data on the interface bond strength of corroded reinforced concrete in the past. The relationship between the factors affecting bond performance and bond strength is explored, and the predictive effect of SVM, RF, and XGB algorithms on bonding strength is discussed. In addition, this model innovatively uses the SHAP method to achieve the interpretability of ML models and overcome the “black box” problem of ML methods. Empirical formulas and ML models are compared as well. The results indicate that the predictive performance of the model far exceeds that of the empirical formula, and the RF model has the best predictive effect. Furthermore, the SHAP method quantitatively confirms that the corrosion rate has the most significant impact on bond strength, which is consistent with experimental observations. Based on the experimental results, the model provides a new choice for addressing the problem of bond strength in corroded reinforced concrete.

A Systematic Study of Stock Markets Using Analytical and AI Techniques

Predicting stock market patterns is seen as a crucial and highly productive activity. Therefore, if investors make wise choices, stock prices will result in significant gains. Investors face a lot of difficulty making predictions about the stock market because of the noisy and stagnating data. As a result, making accurate stock market predictions is difficult for investors who want to put their money to work for them. Predictions of the stock market are made using mathematical techniques and study aids. Out of 30 research papers advocating approaches, this study offers a thorough analysis of each, including computational methodologies, AI algorithms( machine learning and deep learning), performance evaluation parameters, and chosen publications. Research questions are used to choose studies.
 As a result, these chosen studies contribute to the discovery of ML methods and their corresponding data set for predicting security markets. The majority of Artificial Neural Network and Neural Network techniques are employed for producing precise stock market forecasts. The most recent stock market-related prediction system has significant limitations despite the substantial amount of work that has gone into it. In this survey, one may infer that the stock price forecasting procedure is a comprehensive affair and it is very necessary to look more closely at the typical parameters for the stock market prediction.

Cryptographic Money Value Expectation Utilizing ARIMA Model

Abstract: In the beyond couple of years, the cryptocurrency market has developed at a rate that has never been seen. Cryptocurrency works like standard cash, however virtual installments for labor and products are made without the assistance of a national bank or government. Digital money utilizes cryptography to ensure that all exchanges are legitimate and remarkable, however this business is simply beginning, and serious worries have been made about its utilization. To get a full image of individuals' opinion on digital money, it is vital to take a gander at how they feel about it. Along these lines, this study utilizes an assortment of tweets about cryptographic money, which are frequently used to foresee the cost of digital currency available, to do both temperament examination and feeling acknowledgment. A deep learning outfit model called LSTM-GRU is prescribed to deal with the accuracy of the assessment. It integrates two reasons for recurrent neural network: long short-term memory (LSTM) and gated recurrent unit (GRU). LSTM and GRU are collected with the end goal that the GRU gains from the features that LSTM finds. Using term repeat in reverse report repeat, word2vec, and bag-of words (BoW) incorporates, a couple of ML and profound learning methods and a suggested group model are considered. Furthermore, TextBlob and Text2Emotion are looked at to see how they can be used to analyze sentiments. Similarly, more individuals feel blissful when they use cryptographic money. Dread and shock are the following most normal sentiments. The outcomes show that when BoW qualities are utilized, ML models perform better compared to when they don't. The accuracy of the recommended LSTM-GRU gathering for breaking down state of mind and anticipating feelings is 0.99 and 0.92, separately. This is superior to both ML and cutting edge models.

Data-Driven Approach to Analyze Interdependencies between Electrode Manufacturing Parameters and Electrochemical Performance of the Lithium-Ion Battery Cell

The lithium-ion battery cell production is a complex process chain with a high number of process steps and manifold interdependencies. The majority of the properties determining the electrochemical performance of the battery cell are established during electrode manufacturing. An in-depth understanding of electrode manufacturing and its influence on cell performance can pave the way toward high-quality, cost-efficient cell production. Considering the complexity of the process chain and the high share of material costs in battery production, the classic one-factor-at-a-time experimentation is deemed inadequate and expensive.Machine learning (ML) approaches have been proven suitable for analyzing complex process chains. Design of experiment (DoE) methods can be used to generate a sufficient informative database for ML techniques. This study was based on the joint application of DoE and ML methods in electrode manufacturing. For this purpose, in the first step, the response surface methodology (RSM) was used to conduct experiments and analyze the effect of mass loading, drying temperature, and porosity on cell performance. The study was focused on graphite anodes produced at a pilot scale. The electrochemical performance of electrodes was assessed on coin cells at discharge C-rates from C/10 to 5C. Additionally, symmetric coin cells were used to analyze the electrochemical impedance spectra. Supervised machine learning models were adopted to predict the cell characteristics based on the electrode properties. Additionally, a factor analysis reflecting the contribution and importance of each factor on the final cell properties was conducted. The efficient experiment-based data generation using RSM combined with the applied ML techniques can support practitioners towards smart quality-oriented battery cell production.

A metaheuristic-guided machine learning approach for concrete strength prediction with high mix design variability using ultrasonic pulse velocity data

Assessment of concrete strength in existing structures is a common engineering problem. Several attempts in the literature showed the potential of ML methods for predicting concrete strength using concrete properties and NDT values as inputs. However, almost all such ML efforts based on NDT data trained models to predict concrete strength for a specific concrete mix design. We trained a global ML-based model that can predict concrete strength for a wide range of concrete types. This study uses data with high variability for training a metaheuristic-guided ANN model that can cover most concrete mixes used in practice. We put together a dataset that has large variations of mix design components. Training an ANN model using this dataset introduced significant test errors as expected. We optimized hyperparameters, architecture of the ANN model and performed feature selection using genetic algorithm. The proposed model reduces test errors from 9.3 MPa to 4.8 MPa.

Molecular Identification of Acrossocheilus jishouensis (Teleostei: Cyprinidae) and Its Complete Mitochondrial Genome.

Molecular identification, such as DNA barcoding, is a useful tool that is widely applied in distinguishing species. To identify the cyprinid Acrossocheilus jishouensis, which was previously known to be restricted to only its type locality, we conducted molecular identification of this species based on 23 samples in five localities. Molecular identification based on the mitochondrial COI gene sequence showed that the morphologically similar samples from the five populations were all A. jishouensis, as the mean genetic distances between populations were very small (0.1-1.6%); thus, the distribution of this species was substantially expanded. The whole mitochondrial genome of one sample was also assembled, which was 16,594bp in length and consisted of 13 protein-coding genes (PCGs), two rRNA genes, 22 tRNA genes, and one control region. All PCGs began with ATG except the COI gene, which started with GTG; seven PCGs used the complete stop codon TAA, while four terminated in T(AA) and two ended with TAG. The overall base composition reflected a higher proportion of A+T than G+C and a positive AT-skew and negative GC-skew pattern except for the opposite in ND6. Phylogenetic relationships inferred using BI and ML methods revealed that both Acrossocheilus and Onychostoma were nonmonophyletic, which indicated that the traditional diagnoses between these two genera need to be assessed further. The results of this study not only expanded the known distribution ranges of A. jishouensis, but also provided a valuable data resource for future molecular and evolutionary studies of Acrossocheilus and other cyprinids in Barbinae.

Phylogenetic Relationship of Cymbidium Mosaic Virus from the Native Orchids of South Kalimantan, Indonesia

Information on viral genetics, including their phylogenetic relationship, is valuable in controlling viral infection and screening for the development of virus-resistant cultivars in the future. The objectives of this study were to detect and characterize the Cymbidium mosaic virus (CymMV) from the native orchids of South Kalimantan, Indonesia, by the RT-PCR method. Also, to determine their phylogenetic relationship based on a partial genome of RdRp by the ML and PCA methods. Following RT-PCR analysis, one of 10 samples of native orchids used was positively infected by CymMV. In early detection, the RdRp region of CymMV has approximately 530 bp in size. After being sequenced and aligned with other isolates, this region has 121 polymorphic or mutation sites, a GC content of 45.21%, a transition/transversion bias value of 3.52, and nucleotide diversity (0.0415). The phylogenetic analysis revealed that CymMV from South Kalimantan, Indonesia, has closest related to similar isolates from Korea Type 2 (AF016914.1), Niigata, Japan (AB197937.1), Hawaii (EF125180.1), and Taiwan M2 (EU314803.1), with the coefficient divergence of 0.025. But, it has very distantly related to Hawaii 18-1 (EF125178.1) with a coefficient of 0.142. The results provide urgent information in supporting the native orchid's conservation and breeding efforts, locally and globally, including mitigating or controlling the viral infection and screening for the development of virus-free or resistant cultivars in the future.

Use of Synthetic Data in Maritime Applications for the Problem of Steam Turbine Exergy Analysis

Machine learning applications have demonstrated the potential to generate precise models in a wide variety of fields, including marine applications. Still, the main issue with ML-based methods is the need for large amounts of data, which may be impractical to come by. To assure the quality of the models and their robustness to different inputs, synthetic data may be generated using other ML-based methods, such as Triplet Encoded Variable Autoencoder (TVAE), copulas, or a Conditional Tabular Generative Adversarial Network (CTGAN). With this approach, a dataset can be trained using ML methods such as Multilayer Perceptron (MLP) or Extreme Gradient Boosting (XGB) to improve the general performance. The methods are applied to the dataset containing mass flow, temperature, and pressure measurements in seven points of a marine steam turbine as inputs, along with the exergy efficiency (η) and destruction (Ex) of the whole turbine (WT), low-pressure cylinder (LPC) and high-pressure cylinder (HPC) as outputs. The achieved results show that models trained on synthetic data achieve slightly worse results than the models trained on original data in previous research, but allow for the use of as little as two-thirds of the dataset to achieve these results. Using R2 as the main evaluation metric, the best results achieved are 0.99 for ηWT using 100 data points and MLP, 0.93 for ηLPC using 100 data points and an MLP-based model, 0.91 for ηHPC with the same method, and 0.97 for ExWT, 0.96 for ExLPC, and 0.98 for ExHPC using a the XGB trained model with 100 data points.

Towards Diagnostic Aided Systems in Coronary Artery Disease Detection: A Comprehensive Multiview Survey of the State of the Art

Introduction. Coronary artery disease (CAD) is one of the main causes of death all over the world. One way to reduce the mortality rate from CAD is to predict its risk and take effective interventions. The use of machine learning- (ML-) based methods is an effective method for predicting CAD-induced death, which is why many studies in this field have been conducted in recent years. Thus, this study aimed to review published studies on artificial intelligence classification algorithms in CAD detection and diagnosis. Methods. This study systematically reviewed the most cutting-edge techniques for analyzing clinical and paraclinical data to quickly diagnose CAD. We searched PubMed, Scopus, and Web of Science databases using a combination of related keywords. A data extraction form was used to collect data after selecting the articles based on inclusion and exclusion criteria. The content analysis method was used to analyze the data, and based on the study’s objectives, the results are presented in tables and figures. Results. Our search in three prevalent databases resulted in 15689 studies, of which 54 were included to be reviewed for data analysis. Most studies used laboratory and demographic data classification and have shown desirable results. In general, three ML methods (traditional ML, DL/NN, and ensemble) were used. Among the algorithms used, random forest (RF), linear regression (LR), neural networks (NNs), support vector machine (SVM), and K-nearest networks (KNNs) have the most applications in the field of code recognition. Conclusion. The findings of this study show that these models based on different ML methods were successful despite the lack of a benchmark for comparing and analyzing ML features, methods, and algorithms in CAD diagnosis. Many of these models performed better in their analyses of CAD features as a result of a closer look. In the near future, clinical specialists can use ML-based models as a powerful tool for diagnosing CAD more quickly and precisely by looking at its design’s technical facets. Among its incredible outcomes are decreased diagnostic errors, diagnostic time, and needless invasive diagnostic tests, all of which typically result in decreases in diagnostic expenses for healthcare systems.

Exploring the mitochondrial genome of Caridina pseudogracilirostris: a comparative analysis within the Atyidae Family.

Caridina pseudogracilirostris is a highly adaptive estuarine species found in brackish waters and marshes along the southwestern and southern coastal regions of India. The whole mitochondrial genome of C. pseudogracilirostris is 15,451bp in length with 59.3% AT content and encodes 37 genes, including 22 tRNAs, 13 protein-coding genes, and two rRNAs, which are arranged in a distinctive pattern similar to most crustaceans. ML and BI methods were used for phylogenetic analysis of C. pseudogracilirostris clustered with other Caridina species, supporting the monophyly of the Caridina genus within the Atyidae family. The fully annotated mitochondrial genome of C. pseudogracilirostris was submitted to GenBank under accession number OQ534868.1. We are the first to report on the C. pseudogracilirostris whole mitochondrial genome, which provides a valuable resource for future research on genetics, evolution, phylogenetics, etc., among Caridina species and other species. The phylogenetic investigation supports the monophyly of the Caridina genus within the Atyidae family and emphasizes the value of mitochondrial genome data in determining the evolutionary relationships among crustaceans.

Flight departure delay forecasting

The most accurate methods to predict delays have become essential to mitigate their generation and proliferation (and prevent their spread to other airports in the network). Given that both the delay time dependence function and the input variables on which it depends are not fully known, the objective of this research is to predict the delays in the departure of scheduled commercial flights through a methodology that uses predictive tools based on machine learning/deep learning (ML/DL), with supervised training in regression, based on the available flight datasets. The novel contribution of this work is, first, to make a comparison of the predictions in terms of means and statistical variance of the different ML/DL models implemented (ten in total) and, secondly, to determine the coefficients of the importance of the features or flight attributes. Using ML methods known as permutation importance, it is possible to rank the importance of flight attributes by their influence in determining the delay time and reduce the problem of selecting the most important flight attributes. The data for the analysis was obtained from the Colombian airport system for the year 2018. From the results obtained, it is worth mentioning that the model that presents the best performance is the Ensemble, or combination method of Random Forest Regressor models, configured with 2,000 trees within the forest, with an acceptable prediction range measured with the root-mean-square-error (RMSE) metric of 16 to 33 minutes (prediction of time of the flight departure delay) depending on the scenario analysed.

The usage of 10-fold cross-validation and grid search to enhance ML methods performance in solar farm power generation prediction

The usage of 10-fold cross-validation and grid search to enhance ML methods performance in solar farm power generation prediction

Hybrid model for precise hepatitis-C classification using improved random forest and SVM method

Hepatitis C Virus (HCV) is a viral infection that causes liver inflammation. Annually, approximately 3.4 million cases of HCV are reported worldwide. A diagnosis of HCV in earlier stages helps to save lives. In the HCV review, the authors used a single ML-based prediction model in the current research, which encounters several issues, i.e., poor accuracy, data imbalance, and overfitting. This research proposed a Hybrid Predictive Model (HPM) based on an improved random forest and support vector machine to overcome existing research limitations. The proposed model improves a random forest method by adding a bootstrapping approach. The existing RF method is enhanced by adding a bootstrapping process, which helps eliminate the tree’s minor features iteratively to build a strong forest. It improves the performance of the HPM model. The proposed HPM model utilizes a ‘Ranker method’ to rank the dataset features and applies an IRF with SVM, selecting higher-ranked feature elements to build the prediction model. This research uses the online HCV dataset from UCI to measure the proposed model’s performance. The dataset is highly imbalanced; to deal with this issue, we utilized the synthetic minority over-sampling technique (SMOTE). This research performs two experiments. The first experiment is based on data splitting methods, K-fold cross-validation, and training: testing-based splitting. The proposed method achieved an accuracy of 95.89% for k = 5 and 96.29% for k = 10; for the training and testing-based split, the proposed method achieved 91.24% for 80:20 and 92.39% for 70:30, which is the best compared to the existing SVM, MARS, RF, DT, and BGLM methods. In experiment 2, the analysis is performed using feature selection (with SMOTE and without SMOTE). The proposed method achieves an accuracy of 41.541% without SMOTE and 96.82% with SMOTE-based feature selection, which is better than existing ML methods. The experimental results prove the importance of feature selection to achieve higher accuracy in HCV research.

Sentimental Analysis Of COVID-19 Vaccination Tweets Using Machine Learning Techniques

Twitter Sentiment Analysis applies sentiment analysis to data in tweets on social media platforms to identify user sentiment. The scope of research in this field has expanded steadily in recent decades. The reason is that the format of tweets is complex and difficult to process. The extremely small Tweet format introduces a whole new set of problems: B. Use of Slang and Acronyms. The global community remains affected by the ongoing COVID-19 pandemic, with its profound implications for the health and overall welfare of individuals worldwide. Our worldview has changed as a result of the pandemic. A vaccination campaign should be carried out among the population to stop the outbreak of the pandemic. However, people are unsure about vaccination, which is cause for concern. In this study, machine learning techniques were employed to assess the sentiment of public Twitter tweets concerning COVID- 19 vaccination. The researchers utilized two distinct ML methods, namely Support Vector Machine (SVM) and Logistic Regression (LR), to analyze the Twitter data and classify the tweets as either positive or negative. Keywords:Classifier, Twitter, Sentiment Analysis.

Modeling the load carrying capacity of corroded reinforced concrete compression bending members using explainable machine learning

Corrosion of reinforcement can lead to a decrease in the load carrying capacity of reinforced concrete structures and affect their safety. Therefore, accurate evaluation of the ultimate load carrying capacity is crucial for the maintenance and reinforcement of corroded reinforced concrete structures. In this paper, based on experimental research data of 192 corroded reinforced concrete compression bending members, data-driven analysis was conducted using ANN, SVM, RF, and AdaBoost algorithms to establish the relationship between the influencing factors of the load carrying capacity and their ultimate load carrying capacity. The input variables include the section width of the member, section height of the member, length of member, yield strength of reinforcement, diameter of longitudinal reinforcement, compressive strength of concrete, thickness of concrete cover, hoop diameter, original eccentricity, corrosion rate and the ultimate load carrying capacity is the output variable. Additionally, this study innovatively utilizes the Shapley additive explanations (SHAP) method to enhance the interpretability of the ML models, overcoming the "black box" issue associated with ML methods. Furthermore, the performance of the ML models is compared with theoretical formulas. The results indicate that the ML models exhibit good predictive performance, with higher accuracy than thetheoretical calculation formulas. And the predictive performance of ensemble learning models (RF, AdaBoost) is better than that of single learning models (ANN, SVM). The newly developed hybrid ML model is likely to become a new choice for dealing with the load carrying capacity problem of corroded reinforced concrete compression bending members.