Classification Model Research Articles

Development and Validation of a Machine Learning Model for Detection and Classification of Vertigo.

This study aims to investigate whether artificial intelligence can improve the diagnostic accuracy of vertigo related diseases. Based on the clinical guidelines, clinical symptoms and laboratory test results were extracted from electronic medical records as variables. These variables were then input into a machine learning diagnostic model for classification and diagnosis. This study encompasses two primary objectives: Task 1 to distinguish between patients with Benign Paroxysmal Positional Vertigo (BPPV) and non-BPPV. In Task 2, further classifying non-BPPV patients into Ménière's Disease (MD), Vestibular Migraine (VM), and Sudden Sensorineural Hearing Loss accompanied by Vertigo (SSNHLV). The sensitivity, precision, and area under the curve (AUC) metric is primarily used to assess the performance of the machine learning model development phase in a prospective validation cohort. In our study, 1789 patients were recruited as the training cohort and 1148 patients as the prospective validation cohort. The comprehensive diagnostic performance of the XGBoost model surpasses that of traditional models. The sensitivity, accuracy, and AUC in task 1 were 98.32%, 87.03%, and 0.947, respectively. In task 2, the sensitivity values for MD, SSNHLV, and VM were 89.00%, 100.0%, and 79.40%, respectively. The precision values were 88.80%, 100.0%, and 80.00%, respectively. The AUC values were 0.933, 1.000, and 0.931, respectively. The model can significantly improve the accuracy of diagnosing vertigo diseases. This system may enhance the accuracy of classification and diagnosis of vertigo diseases. It offers initial therapy or referrals to clinical doctors, particularly in resource-limited settings. N/A Laryngoscope, 2024.

Generative modeling and augmentation of EEG signals using improved diffusion probabilistic models.

The development of deep learning models for electroencephalography (EEG) signal processing is often constrained by the limited availability of high-quality data. Data augmentation techniques are among the solutions to overcome these challenges, and deep neural generative models, with their data synthesis capabilities, are potential candidates. The current work investigates enhanced diffusion probabilistic models (DPM) and sampling methods for brain signal generation and data augmentation. We used implicit sampling and progressive distillation to shorten the inference and subsequently analysed the effects of these methods on the generated data. To assess the feasibility of our method, four classification models were trained and evaluated in an inter-subject setting on datasets augmented with synthetic signals. Our analysis of generative metrics and statistical evaluations, including subject- and group-level tests, showed that our DPMs could generate visual evoked potentials and motor imagery signals. Distilled, single-step DPMs were trained on two publicly available datasets and were used to synthesize relatively high-quality EEG samples. The performance of the classifiers was improved by the application of the synthesized signals. The present work demonstrates that DPMs are capable of augmenting data with high fidelity and improving the diversity of EEG signals. Although samples can be generated in a single step, there is a significant trade-off between the data quality and sampling steps. The findings and results of this study demonstrate the promising capability of diffusion models for EEG synthesis, which marks progress toward an efficient and generalizable augmentation method for various EEG decoding tasks.

Advancing diagnosis and early risk assessment of preeclampsia through noninvasive cell-free DNA methylation profiling

BackgroundAberrant embryo implantation and suboptimal placentation can lead to (severe) complications such as preeclampsia and fetal growth restriction later in pregnancy. Current identification of high-risk pregnancies relies on a combination of risk factors, biomarkers, and ultrasound examinations, a relatively inaccurate approach.Previously, aberrant DNA methylation due to placental hypoxia has been identified as a potential marker of placental insufficiency and, hence, potential (future) pregnancy complications. The goal of the Early Prediction of prEgnancy Complications Testing, or the ExPECT study, is to validate a genome-wide, cell-free DNA (cfDNA) methylation strategy to diagnose preeclampsia accurately. More importantly, the predictive potential of this strategy is also explored to reliably identify high-risk pregnancies early in gestation. Furthermore, a longitudinal study was conducted, including sequential blood samples from pregnant individuals experiencing both uneventful and complicated gestations, to assess the methylation dynamics of cfDNA throughout these pregnancies.A significant strength of this study is its enzymatic digest, which enriches CpG-rich regions across the genome without the need for proprietary reagents or prior selection of regions of interest. This makes it useful for the cost-effective discovery of novel markers.ResultsInvestigation of methylation patterns throughout pregnancy showed different methylation trends between unaffected and affected pregnancies. We detected differentially methylated regions (DMRs) in pregnancies complicated with preeclampsia as early as 12 weeks of gestation, with distinct differences in the methylation profile between early and late pregnancy. Two classification models were developed to diagnose and predict preeclampsia, demonstrating promising results on a small set of validation samples.ConclusionsThis study offers valuable insights into methylation changes at specific genomic regions throughout pregnancy, revealing critical differences between normal and complicated pregnancies. The power of noninvasive cfDNA methylation profiling was successfully proven, suggesting the potential to integrate this noninvasive approach into routine prenatal care.

A machine learning-based approach using clinopyroxene data to improve accuracy and efficiency in predicting tectonic settings: Implications for Rodinia supercontinent breakup triggered by mantle plume events

Abstract Basalts are ubiquitous mafic rocks found within diverse tectonic settings on Earth. Despite concerted efforts to distinguish tectonic settings through the chemical compositions of basalt, some features of these rocks related to tectonic processes can be obscured by weathering and erosion over geological time, making the discrimination results ambiguous. In this study, we utilized major and trace element data of clinopyroxene in basalts from five distinct tectonic settings: continental within-plate basalts (WPB), island arc basalts (IAB), ocean island basalts (OIB), oceanic floor basalts (OFB), and continental flood basalts (CFB). Employing three machine learning techniques—Multi-layer Perceptron (MLP), Support Vector Machine (SVM), and Random Forest (RF)—we aim to discriminate tectonic settings and magma affinities. Sparse Multinomial Regression (SMR) approach is used to quantitatively discern geochemical signatures that are distinctive of each tectonic setting. The outcomes reveal the efficacy of SVM, which attains an accuracy of 92.1% (major element-based) and 95.2% (major and trace elements-based) for tectonic discrimination. Furthermore, SVM achieves an accuracy of 92.9% (major elements-based) and 95.7% (major and trace elements-based) for magma affinity discrimination. Our study shows that the integration of electron microprobe data from clinopyroxene with machine learning techniques provides an effective approach to distinguish various tectonic settings and magma affinities. The classifier models have been applied to investigate the Neoproterozoic geodynamics of the Jiangnan Orogen. The models show the two pulses of mantle plume events (∼830 Ma and ∼785 Ma) triggering break-up of the Rodinia supercontinent.

Модель обработки и классификации сигналов ЭКГ на основе интеграции CNN, LSTM и метода двойного внимания

Heart rhythm abnormalities diagnosis or classification via electrocardiogram (ECG) in the field of signal processing is regarded as a challenging problem. Classifying ECG signals under the rules of the "Association for the Advancement of Medical Instrumentation (AAMI)" and the inter-patient scheme increases the difficulty of the challenge. AAMI classifies the ECG signal into the following categories: N, S, V, F, and Q. The S category is difficult to detect since its shape pattern is like the N category. To overcome these challenges, this study proposes a novel, robust, end-to-end, and efficient model for ECG signal classification by integrating the "Convolutional Neural Network (CNN)", "Long Short-Term Memory (LSTM)" and dual attention techniques. The architecture of the model includes an encoder-decoder unit built from LSTMs and a dual attention unit with two levels: the first is based on Squeeze-and-Excitation (SE) networks that are incorporated into CNN sections, and they are responsible for weighting the Local Heartbeat Shape Pattern (LHSP) features caught by CNN sections, while the second is based on the Bahdanau scheme, which is incorporated into the encoder-decoder unit, and it is responsible for weighting the Global Heartbeat (GH) features caught by the LSTMs. The suggested model can extract the distinctive features that balance local and global information for optimizing the ECG signal diagnosis. The presented approach is superior to previous methods in the literature and comparable to a cardiologist's performance. The introduced model attained the following F1-Scores: 99.12%, 99.89%, 96.48%, and 99.89% for classifying F, V, S, and N beats, respectively.

3W‐MultiHier: A Three Way Multi‐Hierarchical Model Enabled Deep Learning for Brain Tumor Classification in MRI Scans

AbstractAccurate brain tumor detection and classification are vital for effective diagnosis and treatment planning in medical imaging. Despite advancements in deep learning, challenges such as multimodal complexity, small lesion segmentation, limited training data, and variability in tumor characteristics hinder precise tumor analysis in MRI scans. To address these issues, we propose the Three Way Multi‐Hierarchical Model (3W‐MultiHier) for tumor classification in MRI. 3W‐MultiHier employs a hybrid Capsule‐Transformer UNet (Capsule‐TransUNet) architecture, integrating capsule and transformer networks within the U‐Net framework. This enables the model to capture spatial hierarchies, long‐range dependencies, and global context, ensuring accurate tumor boundary segmentation. The model also incorporates Residual Network Version 2 ‐ Squeeze‐and‐Excitation Network (ResNetV2‐SENet), which excels at extracting complex features through deep hierarchical structures and feature recalibration. Additionally, the Vision Transformer ‐ Transfer Learning (ViT‐TL) pipeline enhances classification accuracy by leveraging fine‐grained hierarchical representations. Extensive evaluations on BraTS (2019, 2020, 2021) datasets demonstrate the superior performance of 3W‐MultiHier, achieving 99.8% accuracy with rapid training and low loss. These results highlight the model's efficiency in handling diverse datasets and its potential to improve clinical diagnostics by enabling precise, reliable brain tumor classification.

Biomarker discovery and development of prognostic prediction model using metabolomic panel in breast cancer patients: a hybrid methodology integrating machine learning and explainable artificial intelligence

BackgroundBreast cancer (BC) is a significant cause of morbidity and mortality in women. Although the important role of metabolism in the molecular pathogenesis of BC is known, there is still a need for robust metabolomic biomarkers and predictive models that will enable the detection and prognosis of BC. This study aims to identify targeted metabolomic biomarker candidates based on explainable artificial intelligence (XAI) for the specific detection of BC.MethodsData obtained after targeted metabolomics analyses using plasma samples from BC patients (n = 102) and healthy controls (n = 99) were used. Machine learning (ML) models based on raw data were developed, then feature selection methods were applied, and the results were compared. SHapley Additive exPlanations (SHAP), an XAI method, was used to clinically explain the decisions of the optimal model in BC prediction.ResultsThe results revealed that variable selection increased the performance of ML models in BC classification, and the optimal model was obtained with the logistic regression (LR) classifier after support vector machine (SVM)-SHAP-based feature selection. SHAP annotations of the LR model revealed that Leucine, isoleucine, L-alloisoleucine, norleucine, and homoserine acids were the most important potential BC diagnostic biomarkers. Combining the identified metabolite markers provided robust BC classification measures with precision, recall, and specificity of 89.50%, 88.38%, and 83.67%, respectively.ConclusionIn conclusion, this study adds valuable information to the discovery of BC biomarkers and underscores the potential of targeted metabolomics-based diagnostic advances in the management of BC.

Transformer model-based multi-scale fine-grained identification and classification of regional traffic states

To address the limitations in precision of conventional traffic state estimation methods, this article introduces a novel approach based on the Transformer model for traffic state identification and classification. Traditional methods commonly categorize traffic states into four or six classes; however, they often fail to accurately capture the nuanced transitions in traffic states before and after the implementation of traffic congestion reduction strategies. Many traffic congestion reduction strategies can alleviate congestion, but they often fail to effectively transition the traffic state from a congested condition to a free-flowing one. To address this issue, we propose a classification framework that divides traffic states into sixteen distinct categories. We design a Transformer model to extract features from traffic data. The k-means algorithm is then applied to these features to group similar traffic states. The resulting clusters are ranked by congestion level using non-dominated sorting, thereby dividing the data into 16 levels, from Level 1 (free-flowing) to Level 16 (congested). Extensive experiments are conducted using a large-scale simulated traffic dataset. The results demonstrate significant advancements in traffic state estimation achieved by our Transformer-based approach. Compared to baseline methods, our model exhibits marked improvements in both clustering quality and generalization capabilities.

A Novel Approach for Lung Cancer Segmentation and Classification Using MSF-Customized ResNet152

This study presents a novel Multi-Scale Fusion-based Customized ResNet152 (MSF-Customized ResNet152) model for lung cancer segmentation and classification, designed to address challenges in class imbalance and feature extraction. The model combines multi-scale feature fusion with depth-wise separable convolution to capture fine and broad image details, enhancing segmentation accuracy. To address the minority representation of cancerous regions, a weighted recall loss was integrated with cross-entropy loss, optimized via Grid Search, to increase sensitivity. Additionally, data augmentation techniques were applied to expand the cancerous image set, further improving detection robustness. The model was evaluated on two datasets: a chest CT-scan dataset and a lung and colon cancer histopathology dataset. Using a 5-fold cross-validation approach, the MSF-Customized ResNet152 achieved a classification accuracy of 98.5%, precision of 98.2%, specificity of 97.2%, F1-score of 97.4%, and Dice coefficient of 97.3%. Comparative analysis demonstrated the superiority of the combined recall and cross-entropy loss function over standard methods, validating the model's effectiveness in handling class imbalance.

Inter-rater reliability in labeling quality and pathological features of retinal OCT scans: A customized annotation software approach.

Various imaging features on optical coherence tomography (OCT) are crucial for identifying and defining disease progression. Establishing a consensus on these imaging features is essential, particularly for training deep learning models for disease classification. This study aims to analyze the inter-rater reliability in labeling the quality and common imaging signatures of retinal OCT scans. 500 OCT scans obtained from CIRRUS HD-OCT 5000 devices were displayed at 512x1024x128 resolution on a customizable, in-house annotation software. Each patient's eye was represented by 16 random scans. Two masked reviewers independently labeled the quality and specific pathological features of each scan. Evaluated features included overall image quality, presence of fovea, and disease signatures including subretinal fluid (SRF), intraretinal fluid (IRF), drusen, pigment epithelial detachment (PED), and hyperreflective material. The raw percentage agreement and Cohen's kappa (κ) coefficient were used to evaluate concurrence between the two sets of labels. Our analysis revealed κ = 0.60 for the inter-rater reliability of overall scan quality, indicating substantial agreement. In contrast, there was slight agreement in determining the cause of poor image quality (κ = 0.18). The binary determination of presence and absence of retinal disease signatures showed almost complete agreement between reviewers (κ = 0.85). Specific retinal pathologies, such as the foveal location of the scan (0.78), IRF (0.63), drusen (0.73), and PED (0.87), exhibited substantial concordance. However, less agreement was found in identifying SRF (0.52), hyperreflective dots (0.41), and hyperreflective foci (0.33). Our study demonstrates significant inter-rater reliability in labeling the quality and retinal pathologies on OCT scans. While some features show stronger agreement than others, these standardized labels can be utilized to create automated machine learning tools for diagnosing retinal diseases and capturing valuable pathological features in each scan. This standardization will aid in the consistency of medical diagnoses and enhance the accessibility of OCT diagnostic tools.

Development and Validation of a Multimodal Machine Learning Model for Diagnosing and Assessing Risk of Crohn's Disease in Patients With Perianal Fistula.

Diagnosis of Crohn's disease (CD) can pose challenges, particularly when perianal fistula is the initial presentation. To develop and validate a predictive model, establishing a visual web tool for early diagnosis of CD in patients presenting with perianal fistula. This retrospective, multicentre validation study involved patients diagnosed with either perianal fistulising CD or cryptoglandular fistula who underwent initial perianal fistula surgery subsequent to rectal MRI at three Chinese centres from September 2016 to December 2020. A random forest classification model was trained on the derivation cohort (n = 550), randomly split into training and test sets at a 7:3 ratio. Validation utilised data from two external centres (n = 300). Model interpretation employed the Shapley Addictive explanation (SHAP) framework. The validated model was integrated into a web tool for calculating patient-specific risk. In the derivation cohort, SHAP analysis highlighted rectal wall ulceration, rectal wall thickening, submucosal fistula, and T2 hyperintensity as risk factors, while age was identified as protective. A random forest classification model developed using these top 5 features achieved an AUROC of 0.9425 (95% CI: 0.8943-0.9906). In the validation cohort, the model performed well with AUROC values of 0.9187 (95% CI: 0.8620-0.9754) and 0.9341 (95% CI: 0.8876-0.9806), respectively. We developed a publicly accessible web-based application. We have developed a multimodal machine learning model and a web tool that can predict and present CD risk in patients initially presenting with perianal fistula.

TCSRNet: a lightweight tobacco leaf curing stage recognition network model

Due to the constraints of the tobacco leaf curing environment and computational resources, current image classification models struggle to balance recognition accuracy and computational efficiency, making practical deployment challenging. To address this issue, this study proposes the development of a lightweight classification network model for recognizing tobacco leaf curing stages (TCSRNet). Firstly, the model utilizes an Inception structure with parallel convolutional branches to capture features at different receptive fields, thereby better adapting to the appearance variations of tobacco leaves at different curing stages. Secondly, the incorporation of Ghost modules significantly reduces the model’s computational complexity and parameter count through parameter sharing, enabling efficient recognition of tobacco leaf curing stages. Lastly, the design of the Multi-scale Adaptive Attention Module (MAAM) enhances the model’s perception of key visual information in images, emphasizing distinctive features such as leaf texture and color, which further improves the model’s accuracy and robustness. On the constructed tobacco leaf curing stage dataset (with color images sized 224×224 pixels), TCSRNet achieves a classification accuracy of 90.35% with 158.136 MFLOPs and 1.749M parameters. Compared to models such as ResNet34, GhostNet, ShuffleNetV2×1.5, EfficientNet-b0, MobileViT-xs, MobileNetV2, MobileNetV3-large, and MobileNetV3-small, TCSRNet demonstrates superior performance in terms of accuracy, FLOPs, and parameter count. Furthermore, when evaluated on the public V2 Plant Seedlings dataset, TCSRNet maintains an impressive accuracy of 97.15% compared to other advanced network models. This research advances the development of lightweight models for recognizing tobacco leaf curing stages, providing theoretical support for smart tobacco curing technologies and injecting new momentum into the digital transformation of the tobacco industry.

A method for dynamically adjusting the difficulty of rehabilitation training tasks driven by attention level.

Enhancements in the rehabilitation of motor and cognitive functions are significantly attainable through proactive patient engagement. The difficulty of rehabilitation tasks and the environment in which they are conducted directly impact patient motivation. Consequently, this study introduces a dynamic difficulty adjustment method for rehabilitation training tasks based on attention levels, designed to adjust task difficulty in real-time and augment the focus of participants on their training tasks. 
Approach: EEG signals from participants were harnessed to train an attention classification model, enabling the acquisition of real-time attention level signals. Task difficulty levels were adjusted based on the fluctuating attention levels. A cohort of 30 participants was engaged to evaluate: (1) the impact on engagement when attention levels are utilized as dynamic difficulty 18 triggers; (2) the influence of various task environments on concentration. The experiment was assessed through EEG signals and questionnaire data, with frequency domain analysis conducted on EEG signals to calculate concentration values and statistical analysis performed on additional data. 
Main Results: The findings reveal that within an identical virtual reality (VR) environment, leveraging attention levels as triggers for difficulty adjustment markedly improves participants' task concentration. Compared to 2D environments, VR environments substantially enhance participants' sense of immersion, interest, and flow state, albeit with increased physical exertion during training. The integration of VR and attention level feedback is deemed the most effective strategy. 
Significance: These exploratory insights indicate that the proposed method paves a novel path for boosting patient engagement in rehabilitation. Immersive rehabilitation training, driven by attention levels, promises a more effective and captivating patient experience. This study advances the field by offering data-driven, personalized rehabilitation approaches, potentially culminating in superior patient outcomes and enhanced quality of life.

Distinguishing novel coronavirus influenza A virus pneumonia with CT radiomics and clinical features

ObjectivesTo differentiate novel coronavirus pneumonia (NCP) with influenza A virus (IAV) pulmonary infection based on computed tomography (CT) radiomics features combined with clinical feature.MethodsA total of 292 patients were enrolled, as NCP determined with reverse-transcription polymerase chain reaction (RT-PCR) and abnormal chest CT findings and IAV pulmonary infection confirmed by nucleic acid test with pneumonia lesion in the chest CT, retrospectively. The dataset was randomly divided into 233 cases in the training set and 59 cases in the validation set according to the ratio of 8:2, and there were 107 cases collected for verification as external test set. Firstly, voxel-based gray-level discretization (binWidth = 25) and Z-Score normalization were applied to preprocess the patient's ROI and normalize the extracted features. Then, the most predictive radiomic features were selected and their corresponding coefficients were evaluated using the correlation coefficient algorithm and the Least Absolute Shrinkage and Selection Operator (LASSO) algorithm. Subsequently, univariate logistic regression was employed to screen for clinically discriminative features from the patient's clinical characteristics. Finally, constructing the radiomics model and clinical model using support vector machines and logistic regression methods, respectively. And then combining these features of the two to construct a combined model. Receiver operating characteristic curve (ROC), calibration curve, and decision curve were performed to evaluate the classification of the radiomics model, clinical model and combined model. Area under ROC curve (AUC) were calculated to evaluate the diagnostic efficiency, and Delong’s test was used to compare the AUC between different models.ResultsAge, white blood cells, neutrophils, lymphocytes, and basic diseases reached statistical significance in the training set. After LASSO, 16 optimal radiomics features were retained. In the validation set and external test set, the SVM radiomics model achieved AUCs of 0.818 and 0.808 for automatic classification of NCP and IAV pulmonary infection,; and the clinical classification model shad AUCs were 0.676 and 0.669; finally, the 5 clinical features and the 16 selected radiomics features were used to construct the combined model with the AUCs of 0.821 and 0.820. After incorporating clinical features, the clinical model’s discriminatory and predictive efficacy further improved in testing sets (AUC, 0.669 vs. 0.820, P = 0.002). The combined model performed well for differentiating the NCP and IAV pulmonary infection, and the calibration curves showed good agreement and decision curves indicated relatively satisfactory clinical benefits.ConclusionThe proposed combined model is feasible and effective in differentiating the NCP and IAV pulmonary infection, which may be used as a convenient and efficient auxiliary tool for radiologists to diagnose noninvasively based on the imaging structure of CT.

Optimization of Cocoa Pods Maturity Classification Using Stacking and Voting with Ensemble Learning Methods in RGB and LAB Spaces

Determining the maturity of cocoa pods early is not just about guaranteeing harvest quality and optimizing yield. It is also about efficient resource management. Rapid identification of the stage of maturity helps avoid losses linked to a premature or late harvest, improving productivity. Early determination of cocoa pod maturity ensures both the quality and quantity of the harvest, as immature or overripe pods cannot produce premium cocoa beans. Our innovative research harnesses artificial intelligence and computer vision technologies to revolutionize the cocoa industry, offering precise and advanced tools for accurately assessing cocoa pod maturity. Providing an objective and rapid assessment enables farmers to make informed decisions about the optimal time to harvest, helping to maximize the yield of their plantations. Furthermore, by automating this process, these technologies reduce the margins for human error and improve the management of agricultural resources. With this in mind, our study proposes to exploit a computer vision method based on the GLCM (gray level co-occurrence matrix) algorithm to extract the characteristics of images in the RGB (red, green, blue) and LAB (luminance, axis between red and green, axis between yellow and blue) color spaces. This approach allows for in-depth image analysis, which is essential for capturing the nuances of cocoa pod maturity. Next, we apply classification algorithms to identify the best performers. These algorithms are then combined via stacking and voting techniques, allowing our model to be optimized by taking advantage of the strengths of each method, thus guaranteeing more robust and precise results. The results demonstrated that the combination of algorithms produced superior performance, especially in the LAB color space, where voting scored 98.49% and stacking 98.71%. In comparison, in the RGB color space, voting scored 96.59% and stacking 97.06%. These results surpass those generally reported in the literature, showing the increased effectiveness of combined approaches in improving the accuracy of classification models. This highlights the importance of exploring ensemble techniques to maximize performance in complex contexts such as cocoa pod maturity classification.

Machine Learning-Based Network Anomaly Detection: Design, Implementation, and Evaluation

Background: In the last decade, numerous methods have been proposed to define and detect outliers, particularly in complex environments like networks, where anomalies significantly deviate from normal patterns. Although defining a clear standard is challenging, anomaly detection systems have become essential for network administrators to efficiently identify and resolve irregularities. Methods: This study develops and evaluates a machine learning-based system for network anomaly detection, focusing on point anomalies within network traffic. It employs both unsupervised and supervised learning techniques, including change point detection, clustering, and classification models, to identify anomalies. SHAP values are utilized to enhance model interpretability. Results: Unsupervised models effectively captured temporal patterns, while supervised models, particularly Random Forest (94.3%), demonstrated high accuracy in classifying anomalies, closely approximating the actual anomaly rate. Conclusions: Experimental results indicate that the system can accurately predict network anomalies in advance. Congestion and packet loss were identified as key factors in anomaly detection. This study demonstrates the potential for real-world deployment of the anomaly detection system to validate its scalability.

Applying Classification Techniques in Machine Learning to Predict Job Satisfaction of University Professors: A Sociodemographic and Occupational Perspective

This article investigates the factors that affect the job satisfaction of university teachers for which 400 teachers from 4 institutions (public and private) in Ecuador were stratified, resulting in a total of 1600 data points collected through online forms. The research was of a cross-sectional design and quantitative and used machine learning techniques of classification and prediction to analyze variables such as ethnic identity, field of knowledge, gender, number of children, job burnout, perceived stress, and occupational risk. The results indicate that the best classification model is neural networks with a precision of 0.7304; the most significant variables for predicting the job satisfaction of university teachers are: the number of children they have, scores related to perceived stress, professional risk, and burnout, province of the university at which the university teacher surveyed works, and city where the teacher works. This is in contrast to marital status, which does not contribute to its prediction. These findings highlight the need for inclusive policies and effective strategies to improve teacher well-being in the university academic environment.

Hybrid bagging and boosting with SHAP based feature selection for enhanced predictive modeling in intrusion detection systems

The novelty and growing sophistication of cyber threats mean that high accuracy and interpretable machine learning models are needed more than ever before for Intrusion Detection and Prevention Systems. This study aims to solve this challenge by applying Explainable AI techniques, including Shapley Additive explanations feature selection, to improve model performance, robustness, and transparency. The method systematically employs different classifiers and proposes a new hybrid method called Hybrid Bagging-Boosting and Boosting on Residuals. Then, performance is taken in four steps: the multistep evaluation of hybrid ensemble learning methods for binary classification and fine-tuning of performance; feature selection using Shapley Additive explanations values retraining the hybrid model for better performance and reducing overfitting; the generalization of the proposed model for multiclass classification; and the evaluation using standard information metrics such as accuracy, precision, recall, and F1-score. Key results indicate that the proposed methods outperform state-of-the-art algorithms, achieving a peak accuracy of 98.47% and an F1 score of 96.19%. These improvements stem from advanced feature selection and resampling techniques, enhancing model accuracy and balancing precision and recall. Integrating Shapley Additive explanations-based feature selection with hybrid ensemble methods significantly boosts the predictive and explanatory power of Intrusion Detection and Prevention Systems, addressing common pitfalls in traditional cybersecurity models. This study paves the way for further research on statistical innovations to enhance Intrusion Detection and Prevention Systems performance.

A Comprehensive CNN Model for Age-Related Macular Degeneration Classification Using OCT: Integrating Inception Modules, SE Blocks, and ConvMixer

Background/Objectives: Age-related macular degeneration (AMD) is a significant cause of vision loss in older adults, often progressing without early noticeable symptoms. Deep learning (DL) models, particularly convolutional neural networks (CNNs), demonstrate potential in accurately diagnosing and classifying AMD using medical imaging technologies like optical coherence to-mography (OCT) scans. This study introduces a novel CNN-based DL method for AMD diagnosis, aiming to enhance computational efficiency and classification accuracy. Methods: The proposed method (PM) combines modified Inception modules, Depthwise Squeeze-and-Excitation Blocks, and ConvMixer architecture. Its effectiveness was evaluated on two datasets: a private dataset with 2316 images and the public Noor dataset. Key performance metrics, including accuracy, precision, recall, and F1 score, were calculated to assess the method’s diagnostic performance. Results: On the private dataset, the PM achieved outstanding performance: 97.98% accuracy, 97.95% precision, 97.77% recall, and 97.86% F1 score. When tested on the public Noor dataset, the method reached 100% across all evaluation metrics, outperforming existing DL approaches. Conclusions: These results highlight the promising role of AI-based systems in AMD diagnosis, of-fering advanced feature extraction capabilities that can potentially enable early detection and in-tervention, ultimately improving patient care and outcomes. While the proposed model demon-strates promising performance on the datasets tested, the study is limited by the size and diversity of the datasets. Future work will focus on external clinical validation to address these limita-tions.

SSMBERT: A Space Science Mission Requirement Classification Method Based on BERT

Model-Based Systems Engineering (MBSE) has demonstrated importance in the aerospace field. However, the MBSE modeling process is often tedious and heavily reliant on specialized knowledge and experience; thus, a new modeling method is urgently required to enhance modeling efficiency. This article focuses on the MBSE modeling in space science mission phase 0, during which the mission requirements are collected, and the corresponding dataset is constructed. The dataset is utilized to fine-tune the BERT pre-training model for the classification of requirements pertaining to space science missions. This process supports the subsequent automated creation of the MBSE requirement model, which aims to facilitate scientific objective analysis and enhances the overall efficiency of the space science mission design process. Based on the characteristics of space science missions, this paper categorized the requirements into four categories: scientific objectives, performance, payload, and engineering requirements, and constructed a requirements dataset for space science missions. Then, utilizing this dataset, the BERT model is fine-tuned to obtain a space science mission requirements classification model (SSMBERT). Finally, SSMBERT is compared with other models, including TextCNN, TextRNN, and GPT-2, in the context of the space science mission requirement classification task. The results indicate that SSMBERT performs effectively under Few-Shot conditions, achieving a precision of 95%, which is at least 10% higher than other models, demonstrating superior performance and generalization capabilities.