Conventional Machine Learning Algorithms Research Articles

Generative adversarial network model to classify human induced pluripotent stem cell-cardiomyocytes based on maturation level

Our study develops a generative adversarial network (GAN)-based method that generates faithful synthetic image data of human cardiomyocytes at varying stages in their maturation process, as a tool to significantly enhance the classification accuracy of cells and ultimately assist the throughput of computational analysis of cellular structure and functions. Human induced pluripotent stem cell derived cardiomyocytes (hiPSC-CMs) were cultured on micropatterned collagen coated hydrogels of physiological stiffnesses to facilitate maturation and optical measurements were performed for their structural and functional analyses. Control groups were cultured on collagen coated glass well plates. These image recordings were used as the real data to train the GAN model. The results show the GAN approach is able to replicate true features from the real data, and inclusion of such synthetic data significantly improves the classification accuracy compared to usage of only real experimental data that is often limited in scale and diversity. The proposed model outperformed four conventional machine learning algorithms with respect to improved data generalization ability and data classification by incorporating synthetic data. This work demonstrates the importance of integrating synthetic data in situations where there are limited sample sizes and thus, effectively addresses the challenges imposed by data availability.

Optimized Machine Learning Algorithms for Predicting the Punching Shear Resistance of Flat Slabs with Transverse Reinforcement

In the calculation of reinforced concrete (RC) flat slabs with transverse reinforcement, punching shear resistance is one of the most critical factors. It is true that design provisions may be implemented, but they often result in significant biases and deviations from expectations. This study aims to present an optimized machine learning (ML) algorithm for estimating the punching shear resistance. Four machine learning (ML) algorithms (SVR, DT, RF, and XGBoost) with Bayesian optimization (BO) are presented in this paper to provide accurate predictions for flat slabs. The adoptability and optimization of the models are achieved through the analysis of a database of 337 test specimens with nine design parameters. Machine learning (ML) techniques are used to estimate punching shear resistance, which is compared with design provisions and equations relating to critical shear crack theory (CSCT). According to this study, Bayesian optimization is still capable of improving the performance of conventional machine learning algorithms, while the XGBoost-based model offers advanced capabilities. Predictions based on BO-XGBoost are in good agreement with actual values (MAE, RMSE, and R2 are 0.09 MN, 0.14 MN, and 0.92, respectively) in test set. Following a detailed explanation using Shapley additive explanation (SHAP), a high-performance ML approach is used to investigate the predictive results. With the proposed optimized algorithms, it is possible to determine the punching shear resistance of flat slabs with transverse reinforcement during the preliminary stages of the construction.

A New Winter Wheat Crop Segmentation Method Based on a New Fast-UNet Model and Multi-Temporal Sentinel-2 Images

Mapping and monitoring crops are the most complex and difficult tasks for experts processing and analyzing remote sensing (RS) images. Classifying crops using RS images is the most expensive task, and it requires intensive labor, especially in the sample collection phase. Fieldwork requires periodic visits to collect data about the crop’s physiochemical characteristics and separating them using the known conventional machine learning algorithms and remote sensing images. As the problem becomes more complex because of the diversity of crop types and the increase in area size, sample collection becomes more complex and unreliable. To avoid these problems, a new segmentation model was created that does not require sample collection or high-resolution images and can successfully distinguish wheat from other crops. Moreover, UNet is a well-known Convolutional Neural Network (CNN), and the semantic method was adjusted to become more powerful, faster, and use fewer resources. The new model was named Fast-UNet and was used to improve the segmentation of wheat crops. Fast-UNet was compared to UNet and Google’s newly developed semantic segmentation model, DeepLabV3+. The new model was faster than the compared models, and it had the highest average accuracy compared to UNet and DeepLabV3+, with values of 93.45, 93.05, and 92.56 respectively. Finally, new datasets of time series NDVI images and ground truth data were created. These datasets, and the newly developed model, were made available publicly on the Web.

Applications of artificial intelligence in interventional oncology: An up-to-date review of the literature.

Interventional oncology provides image-guided therapies, including transarterial tumor embolization and percutaneous tumor ablation, for malignant tumors in a minimally invasive manner. As in other medical fields, the application of artificial intelligence (AI) in interventional oncology has garnered significant attention. This narrative review describes the current state of AI applications in interventional oncology based on recent literature. A literature search revealed a rapid increase in the number of studies relevant to this topic recently. Investigators have attempted to use AI for various tasks, including automatic segmentation of organs, tumors, and treatment areas; treatment simulation; improvement of intraprocedural image quality; prediction of treatment outcomes; and detection of post-treatment recurrence. Among these, the AI-based prediction of treatment outcomes has been the most studied. Various deep and conventional machine learning algorithms have been proposed for these tasks. Radiomics has often been incorporated into prediction and detection models. Current literature suggests that AI is potentially useful in various aspects of interventional oncology, from treatment planning to post-treatment follow-up. However, most AI-based methods discussed in this review are still at the research stage, and few have been implemented in clinical practice. To achieve widespread adoption of AI technologies in interventional oncology procedures, further research on their reliability and clinical utility is necessary. Nevertheless, considering the rapid research progress in this field, various AI technologies will be integrated into interventional oncology practices in the near future.

Machine learning based Parkinson’s disease detection and progression evaluation using gray and white matter segmentation from 3D MRI

Parkinson’s disease (PD) is a movement-related neurological condition caused by the death of brain nerve cells that produce dopamine. T1 MR images were obtained from the Parkinson’s Progression Markers Initiative (PPMI) database. Data was collected at baseline, and at 48 months duration. SPM12 software was used to segment gray matter (GM) and white matter (WM) from the MR images. For the classification of PD, CNN and machine learning (ML) classifiers were used to train on the segmented GM and WM. The findings demonstrated that utilizing the segmented GM and WM obtained from MR images at 48 months had a better predictive ability than the data obtainment at the baseline. CNNs did not perform as well as the conventional ML algorithms, especially for the baseline data. This result is most likely due to the smaller dataset available for training the CNNs, as CNNs normally require more data for best performance. Overall, machine learning algorithms were able to distinguish between people with Parkinson’s disease and healthy controls by analyzing GM and WM in brain scans. The classifiers trained at different stages demonstrated varying degrees of accuracy, with the predictive accuracy for the 48-month dataset surpassing that of the baseline data by a significant margin. The accuracy rate for GM was 65.78% at baseline and improved significantly to 92.59% at 48 months. Similarly, the accuracy rate for WM was 60.52% at baseline and improved to 88.89% at 48 months.

A novel energy management of public charging stations using attention-based deep learning model

Electricity grids are complex systems that must balance the supply and demand of electricity in real-time. However, with the increasing adoption of electric vehicles (EVs), managing the grid’s stability has become more challenging. EV charging can cause spikes in electricity demand, leading to peak demand periods that strain the power grid’s infrastructure. With the help of load forecasting, this effect on the grid can be mitigated by predicting the charging demand of electric vehicles in advance. This will help utilities adjust their energy supply in real-time, ensuring enough energy is available to meet demand, and preventing overloads or under utilization of the grid. Moreover, the EV charging demand is influenced by a wide range of factors, including charging station locations, weather, and time of day. Therefore, advanced deep learning models are required to learn these complex relationships and identify patterns in EV charging demand, enabling utilities to make more informed decisions. In this research, an attention-based deep learning approach is proposed for more accurate prediction of EV load demand. This novel approach integrates attention mechanisms with traditional deep learning models like LSTM and GRU, allowing the model to dynamically weight the importance of different features and focus on the most relevant information. The outcomes are compared to conventional deep learning and machine learning algorithms. To test the efficacy of the proposed framework, an actual ACN dataset for public EV charging stations is utilized.

David vs. Goliath: comparing conventional machine learning and a large language model for assessing students' concept use in a physics problem.

Large language models have been shown to excel in many different tasks across disciplines and research sites. They provide novel opportunities to enhance educational research and instruction in different ways such as assessment. However, these methods have also been shown to have fundamental limitations. These relate, among others, to hallucinating knowledge, explainability of model decisions, and resource expenditure. As such, more conventional machine learning algorithms might be more convenient for specific research problems because they allow researchers more control over their research. Yet, the circumstances in which either conventional machine learning or large language models are preferable choices are not well understood. This study seeks to answer the question to what extent either conventional machine learning algorithms or a recently advanced large language model performs better in assessing students' concept use in a physics problem-solving task. We found that conventional machine learning algorithms in combination outperformed the large language model. Model decisions were then analyzed via closer examination of the models' classifications. We conclude that in specific contexts, conventional machine learning can supplement large language models, especially when labeled data is available.

Enhancing Myocardial Infarction Diagnosis: LSTM-based Deep Learning Approach Integrating Echocardiographic Wall Motion Analysis

PurposeOwing to the increased mortality of heart diseases worldwide, especially myocardial infarction (MI), early detection is essential for improved diagnosis and treatment. The main purpose of this study is to develop a myocardial infarction detection method that combines deep learning and image processing, focusing on abnormalities in left ventricular (LV) wall motion.MethodsThe proposed method primarily uses the LV wall motion movement as a feature to train an LSTM network for MI detection. LV wall motion annotated by expert cardiologists was used as the ground truth. Accuracy, sensitivity, specificity, and area under the curve (AUC) were used to evaluate model performance. The proposed method primarily uses LV wall motion as a feature, combined with LV size and image pixels, to improve diagnostic accuracy over existing computer-aided design (CAD) systems.ResultsThe LSTM model achieved the highest diagnostic performance when trained on a combination of LV wall motion, LV size, and image pixel features with an accuracy of 95%, sensitivity of 96%, specificity of 94%, and an AUC value of 0.98. The LSTM model significantly outperformed models trained on individual feature sets or conventional machine learning algorithms. The inclusion of LV wall motion analysis improved accuracy by 10% compared to using only LV size and pixel data.ConclusionOur MI diagnosis system uses echocardiographic image analysis and LSTM-based deep learning to accurately detect LV wall motion issues related to MI. Compared with current CAD systems, the inclusion of LV wall motion analysis significantly improves diagnosis accuracy. The proposed system can help physicians detect MI early, thereby accelerating treatment and improving patient outcomes.

A lightweight intrusion detection algorithm for IoT based on data purification and a separable convolution improved CNN

With the rapid development of the IoT (Internet of Things), the network data present the characteristics of large volume and high dimension. Convolutional neural networks (CNNs) have become one of the most important intrusion detection methods due to their advantages in processing high-dimensional data. The conventional intrusion detection model based on CNN lacks an effective data purification means in the process of converting unstructured data into image data, and too many parameters are generated due to the complex structure of the model in the training process, leading to the problems of high time complexity and low detection rate of the model, which limits the application of the CNN in intrusion detection of the IoT. First, based on the principle of liquid molecular distillation, a data purification algorithm (DPA) for unstructured data is proposed in this paper, which reduces the "redundant" data generated in the process of converting unstructured data to image data. Second, based on the rigid-motion convolution principle of a separable wavelet, separable convolution is used to improve the CNN structure, and then a lightweight detection algorithm LSCNN (lightweight CNN based on separable convolution) is developed to reduce the number of parameters in the network structure and improve the time efficiency and accuracy of the algorithm. The experimental results on real intrusion detection datasets show that the LSCNN trained on DPA purified data has higher time efficiency and detection accuracy than the conventional CNN, and compared with the conventional machine learning algorithm, it has higher accuracy.

Deep Feature Extraction with SVM Classifier for Brain Tumor Classification

Recently, methods for classifying brain tumors have used Deep Learning (DL), in particular, Convolutional Neural Networks (CNNs), to obtain promising results. Unlike conventional Machine Learning (ML) algorithms, CNNs can automatically extract features from images; they do not, however, need the extraction regarding hand-crafted features. Many obstacles reduce the accuracy of brain tumor classification systems; to address such obstacles, we propose a DL-based feature extraction method for brain tumor classification. A total of two pretrained CNNs, VggNet-16 and ResNet-18, are applied as deep feature extractors in the scheme to accomplish deep feature extraction. Contrast Limited Adaptive Histogram Equalization (CLAHE) technique has been first used for enhancing the images. Second, each separately pretrained CNN, VggNet-16 and ResNet-18, is used for extracting the deep features from Magnetic Resonance Imaging (MRI). Lastly, a Multiclass Support Vector Machines (Multiclass -SVM) classifier is used to complete a classification task. Tests conducted on the aforementioned datasets: the effectiveness of the suggested approach is demonstrated by the CE-MRI Figshare, the REMBRANDT, and the Brain Tumor Classification, where the pre-trained CNN models and SVM classifier enhance performance. Specifically, the pretrained CNN with SVM approach produces accuracy ranging from 95.28% to 98.62% across all data-sets.

Structured adaptive boosting trees for detection of multicellular aggregates in fluorescence intravital microscopy

Fluorescence intravital microscopy captures large data sets of dynamic multicellular interactions within various organs such as the lungs, liver, and brain of living subjects. In medical imaging, edge detection is used to accurately identify and delineate important structures and boundaries inside the images. To improve edge sharpness, edge detection frequently requires the inclusion of low-level features. Herein, a machine learning approach is needed to automate the edge detection of multicellular aggregates of distinctly labeled blood cells within the microcirculation. In this work, the Structured Adaptive Boosting Trees algorithm (AdaBoost.S) is proposed as a contribution to overcome some of the edge detection challenges related to medical images. Algorithm design is based on the observation that edges over an image mask often exhibit special structures and are interdependent. Such structures can be predicted using the features extracted from a bigger image patch that covers the image edge mask. The proposed AdaBoost.S is applied to detect multicellular aggregates within blood vessels from the fluorescence lung intravital images of mice exposed to e-cigarette vapor. The predictive capabilities of this approach for detecting platelet-neutrophil aggregates within the lung blood vessels are evaluated against three conventional machine learning algorithms: Random Forest, XGBoost and Decision Tree. AdaBoost.S exhibits a mean recall, F-score, and precision of 0.81, 0.79, and 0.78, respectively. Compared to all three existing algorithms, AdaBoost.S has statistically better performance for recall and F-score. Although AdaBoost.S does not outperform Random Forest in precision, it remains superior to the XGBoost and Decision Tree algorithms. The proposed AdaBoost.S is widely applicable to analysis of other fluorescence intravital microscopy applications including cancer, infection, and cardiovascular disease.

Natural Language Processing Accurately Differentiates Cancer Symptom Information in Electronic Health Record Narratives.

Identifying cancer symptoms in electronic health record (EHR) narratives is feasible with natural language processing (NLP). However, more efficient NLP systems are needed to detect various symptoms and distinguish observed symptoms from negated symptoms and medication-related side effects. We evaluated the accuracy of NLP in (1) detecting 14 symptom groups (ie, pain, fatigue, swelling, depressed mood, anxiety, nausea/vomiting, pruritus, headache, shortness of breath, constipation, numbness/tingling, decreased appetite, impaired memory, disturbed sleep) and (2) distinguishing observed symptoms in EHR narratives among patients with cancer. We extracted 902,508 notes for 11,784 unique patients diagnosed with cancer and developed a gold standard corpus of 1,112 notes labeled for presence or absence of 14 symptom groups. We trained an embeddings-augmented NLP system integrating human and machine intelligence and conventional machine learning algorithms. NLP metrics were calculated on a gold standard corpus subset for testing. The interannotator agreement for labeling the gold standard corpus was excellent at 92%. The embeddings-augmented NLP model achieved the best performance (F1 score = 0.877). The highest NLP accuracy was observed in pruritus (F1 score = 0.937) while the lowest accuracy was in swelling (F1 score = 0.787). After classifying the entire data set with embeddings-augmented NLP, we found that 41% of the notes included symptom documentation. Pain was the most documented symptom (29% of all notes) while impaired memory was the least documented (0.7% of all notes). We illustrated the feasibility of detecting 14 symptom groups in EHR narratives and showed that an embeddings-augmented NLP system outperforms conventional machine learning algorithms in detecting symptom information and differentiating observed symptoms from negated symptoms and medication-related side effects.

Self-organizing hierarchical incremental learning framework and universal approximation analysis based on stochastic configuration mechanism

Conventional machine learning algorithms face significant limitations when dealing with high-dimensional data. Besides, deep learning models often require substantial computational resources and have a high processing time despite their excellent performance. Hence, this paper proposes an expanded stochastic configuration network and a self-organizing hierarchical incremental learning (SHIL) framework to overcome these challenges. Specifically, this study introduces a novel supervised hierarchical clustering tree based on the minimum redundancy maximum correlation algorithm, which mines internal data structures to construct diverse hierarchies. Subsequently, by exploiting the parent-child node relationships in the tree structure, SHIL defines the maximum number of nodes as the switching condition between levels uses the supervisory mechanism as the parameter selection criterion, and adopts the tolerance error as the termination criterion for the training. Furthermore, the universal approximation property of the SHIL framework is provided. The proposed SHIL framework is validated on several benchmark datasets, image datasets, and industrial robot cases, with the corresponding experimental results demonstrating that SHIL significantly improves computational efficiency and ensures high accuracy.

Prediction of fatigue life of laminated composites by integrating artificial neural network model and non-dominated sorting genetic algorithm

The present study introduces an artificial neural network (ANN) model coupled with the non-dominated sorting genetic algorithm (NSGA-II) to establish an advanced model for fatigue life prediction of laminated composites. The developed model was trained on a comprehensive collection of dependent experimental data of carbon/epoxy composites. This training encompassed 14 distinct cases, covering various stress concentration geometries, loading levels, and stacking sequences to ensure the model’s robustness and generality. A data augmentation technique was employed to generate similar data to enrich the datasets. The best-obtained accuracy from the model, as measured by the coefficient of determination (R2 score), was 88% and 90% for the test and validation datasets, respectively. While using the data augmentation method, these values improved to 97% and 98%, respectively. The results from the model were compared to those of more conventional regression machine learning algorithms, such as decision trees and gradient boosting. To emphasize the superior predictive accuracy of the developed model, it is essential to note that the best R2 score obtained for the test and validation datasets was 68% using conventional models.

Laser-Induced Breakdown Spectroscopy-Visible and Near-Infrared Spectroscopy Fusion Based on Deep Learning Network for Identification of Adulterated Polygonati Rhizoma.

The geographical origin of foods greatly influences their quality and price, leading to adulteration between high-priced and low-priced regions in the market. The rapid detection of such adulteration is crucial for food safety and fair competition. To detect the adulteration of Polygonati Rhizoma from different regions, we proposed LIBS-VNIR fusion based on the deep learning network (LVDLNet), which combines laser-induced breakdown spectroscopy (LIBS) containing element information with visible and near-infrared spectroscopy (VNIR) containing molecular information. The LVDLNet model achieved accuracy of 98.75%, macro-F measure of 98.50%, macro-precision of 98.78%, and macro-recall of 98.75%. The model, which increased these metrics from about 87% for LIBS and about 93% for VNIR to more than 98%, significantly improved the identification ability. Furthermore, tests on different adulterated source samples confirmed the model's robustness, with all metrics improving from about 87% for LIBS and 86% for VNIR to above 96%. Compared to conventional machine learning algorithms, LVDLNet also demonstrated its superior performance. The results indicated that the LVDLNet model can effectively integrate element information and molecular information to identify the adulterated Polygonati Rhizoma. This work shows that the scheme is a potent tool for food identification applications.

Transfer Learning in Weather Prediction: Why, How, and What Should

Transfer learning (TL) is a popular phrase in deep learning (DL) domain. It is one of the latest artificial intelligence (AI) technologies that has a significant impact on big data analysis. Methods of traditional machine learning (ML) require the availability of an adequate quantity of training data as well as similarity of characteristics among the feature spaces corresponding to training and test data while performing supervised learning tasks. However, in real-life analytical problems, data scarcity often arises. In such scenarios, the TL approach has shown effectiveness in transferring knowledge from the source tasks that had large training data to a target task that has less training data. Basically, in TL, a model that has been trained on one task is essentially applied to a second related (but not exact) task. In this way, the issue of distribution mismatch can also be addressed. TL is not like conventional machine learning algorithms that try to learn each task starting from the beginning. Meteorological research is such an example of big data analysis which often faces the data scarcity issue. The current study addresses the contemporary challenges in weather forecasting that can be solved (or better dealt with) using TL methods. It presents a brief review of earlier research, followed by potential applications of TL algorithms to several key challenges in weather prediction, which includes the prediction of air quality, thunderstorms, precipitation, visibility, and cyclones, among others. Special emphasis is given to high-impact weather (HIW) prediction. These high-impact events are extremely difficult to predict, and they can cause enormous property damage and fatalities around the world. TL techniques have shown advantages in predicting HIW. Various challenging issues in implementing TL technology are then discussed. Finally, we address various prospects associated with TL, propose new research directions, and more importantly mention some concerns for beginners in DL-TL research. An extensive list of references is also provided.

Identification and diagnosis of schizophrenia based on multichannel EEG and CNN deep learning model

This paper proposes a high-accuracy EEG-based schizophrenia (SZ) detection approach. Unlike comparable literature studies employing conventional machine learning algorithms, our method autonomously extracts the necessary features for network training from EEG recordings. The proposed model is a ten-layered CNN that contains a max pooling layer, a Global Average Pooling layer, four convolution layers, two dropout layers for overfitting prevention, and two fully connected layers. The efficiency of the suggested method was assessed using the ten-fold-cross validation technique and the EEG records of 14 healthy subjects and 14 SZ patients. The obtained mean accuracy score was 99.18 %. To confirm the high mean accuracy attained, we tested the model on unseen data with a near-perfect accuracy score (almost 100 %). In addition, the results we obtained outperform numerous other comparable works.

A Novel Hybrid Feature Extraction Methods for EEG Based Emotions Classification Using Ensemble Approaches in HIED Dataset

Introduction: Emotions play a significant role in human relationships in everyday challenges. Human-machine interactions and the complexities of its research include humanoid robots which rely significantly on emotional queries. The present study recommends a novel methodology for human emotion identification using electroencephalogram (EEG) signals. Machine learning (ML) techniques based on electroencephalogram have demonstrated impressive results in distinguishing emotions. Method: The present study investigates five ensemble learning-based machine learning (EML) and five conventional machine learning (CML) algorithms for achieving the recognition of human emotions from EEG signals. The main objective of the current research study is to implement the optimal approach for classifying emotions and subsequently will achieve it by using physiological characteristics to categorise the seven main emotional states (stress, happy, sadness, anger, fear, disgust, and surprise). This research follows the study investigation of ensemble learning-based machine learning (EML) and conventional machine learning (CML) algorithms for achieving the recognition of human emotions from EEG signals. Initially, the EEG data in this study are categorized into theta, alpha, beta, and gamma bands using a DWT. Result: With this idea, the research elaborates on further decomposition based on bandseparated EEG signals known as intrinsic mode functions (IMFs) along with empirical mode decomposition is subsequently implemented. Then, 13 statistical characteristics are extracted from the IMFs using five multiclass EML algorithms: adaptive boosting, rotation random forest, bagging, random forest, and extreme gradient boost. The following procedure is carried out to construct an ML-based system. In the final phase, 10-fold cross-validation is used to assess the efficacy of these five EML algorithms. Accuracy, F1-score, and area-under-the-curve (AUC) are performance assessment metrics that are employed to compare the final results of these algorithms with the five CML techniques. Conclusion: The proposed method for EEG-based emotion analysis is significantly more effective and achieves greater outcomes than all of the techniques that were compared, based on the data from the experiments.

MediaPipe with GNN for Human Activity Recognition

Human interaction and computer vision converge in the realm of Human Activity Recognition (HAR), which is a research field dedicated to the creation of automated systems capable of observing and categorizing human activities. This domain closely aligns with machine learning, involving the development of algorithms and models adept at learning to recognize and classify patterns within data. HAR typically unfolds in two pivotal phases: data acquisition and processing, followed by activity classification. In the initial phase of data acquisition and processing, information is gathered from various sensors or video sources, such as accelerometers, smartphones, or smartwatches. Subsequently, the collected data undergo preprocessing to extract relevant features. The subsequent phase, activity classification, employs machine learning algorithms to categorize these extracted features into distinct activity types, ranging from walking and running to sitting. This paper introduces an innovative approach grounded on these two fundamental phases. For the first phase, we leverage the MediaPipe algorithm to discern human articulations. Once these poses are detected, we contribute by extracting the coordinates of each articulation. These coordinates are then transformed into graphs, where nodes signify the articulation coordinates and edges represent the connections between them. In the second phase, we enhance existing methodologies by incorporating a diverse set of machine learning models. Notably, the utilization of Graph Neural Networks (GNNs) which stands out as a significant advancement. This choice proves instrumental in effectively learning and representing complex spatial and temporal patterns, surpassing the limi-tations of conventional machine learning algorithms. The developed system undergoes evaluation on the KTH and UCF50 datasets, demonstrating state-of-the-art performance in HAR.

Meta-2OM: A multi-classifier meta-model for the accurate prediction of RNA 2'-O-methylation sites in human RNA.

2'-O-methylation (2-OM or Nm) is a widespread RNA modification observed in various RNA types like tRNA, mRNA, rRNA, miRNA, piRNA, and snRNA, which plays a crucial role in several biological functional mechanisms and innate immunity. To comprehend its modification mechanisms and potential epigenetic regulation, it is necessary to accurately identify 2-OM sites. However, biological experiments can be tedious, time-consuming, and expensive. Furthermore, currently available computational methods face challenges due to inadequate datasets and limited classification capabilities. To address these challenges, we proposed Meta-2OM, a cutting-edge predictor that can accurately identify 2-OM sites in human RNA. In brief, we applied a meta-learning approach that considered eight conventional machine learning algorithms, including tree-based classifiers and decision boundary-based classifiers, and eighteen different feature encoding algorithms that cover physicochemical, compositional, position-specific and natural language processing information. The predicted probabilities of 2-OM sites from the baseline models are then combined and trained using logistic regression to generate the final prediction. Consequently, Meta-2OM achieved excellent performance in both 5-fold cross-validation training and independent testing, outperforming all existing state-of-the-art methods. Specifically, on the independent test set, Meta-2OM achieved an overall accuracy of 0.870, sensitivity of 0.836, specificity of 0.904, and Matthew's correlation coefficient of 0.743. To facilitate its use, a user-friendly web server and standalone program have been developed and freely available at http://kurata35.bio.kyutech.ac.jp/Meta-2OM and https://github.com/kuratahiroyuki/Meta-2OM.