Search Results (364)

Cancer metabolic reprogramming plays a critical role in tumor progression and therapeutic resistance, underscoring the need for advanced analytical strategies. Metabolomics, leveraging mass spectrometry and nuclear magnetic resonance (NMR) spectroscopy, offers a comprehensive and functional readout of tumor biochemistry. By enabling both targeted metabolite quantification and untargeted profiling, metabolomics captures the dynamic metabolic alterations associated with cancer. The integration of metabolomics with machine learning (ML) approaches further enhances the interpretation of these complex, high-dimensional datasets, providing powerful insights into cancer biology from biomarker discovery to therapeutic targeting. This review systematically examines the transformative role of ML in cancer metabolomics. We discuss how various ML methodologies—including supervised algorithms (e.g., Support Vector Machine, Random Forest), unsupervised techniques (e.g., Principal Component Analysis, t-SNE), and deep learning frameworks—are advancing cancer research. Specifically, we highlight three major applications of ML–metabolomics integration: (1) cancer subtyping, exemplified by the use of Similarity Network Fusion (SNF) and LASSO regression to classify triple-negative breast cancer into subtypes with distinct survival outcomes; (2) biomarker discovery, where Random Forest and Partial Least Squares Discriminant Analysis (PLS-DA) models have achieved >90% accuracy in detecting breast and colorectal cancers through biofluid metabolomics; and (3) prognostic modeling, demonstrated by the identification of race-specific metabolic signatures in breast cancer and the prediction of clinical outcomes in lung and ovarian cancers. Beyond these areas, we explore applications across prostate, thyroid, and pancreatic cancers, where ML-driven metabolomics is contributing to earlier detection, improved risk stratification, and personalized treatment planning. We also address critical challenges, including issues of data quality (e.g., batch effects, missing values), model interpretability, and barriers to clinical translation. Emerging solutions, such as explainable artificial intelligence (XAI) approaches and standardized multi-omics integration pipelines, are discussed as pathways to overcome these hurdles. By synthesizing recent advances, this review illustrates how ML-enhanced metabolomics bridges the gap between fundamental cancer metabolism research and clinical application, offering new avenues for precision oncology through improved diagnosis, prognosis, and tailored therapeutic strategies. Full article

Network Intrusion Detection Systems (NIDS) driven by Machine Learning (ML) algorithms are usually trained using publicly available datasets consisting of labeled traffic samples, where labels refer to traffic classes, usually one benign and multiple harmful. This paper studies the generalizability of models trained on such datasets. This issue is crucial given the application of such a model to actual internet traffic because high-performance measures obtained on datasets do not necessarily imply similar efficiency on the real traffic. We propose a procedure consisting of cross-validation using various sets sharing some standard traffic classes combined with the t-SNE visualization. We apply it to investigate four well-known and widely used datasets: UNSW-NB15, CIC-CSE-IDS2018, BoT-IoT, and ToN-IoT. Our investigation reveals that the high accuracy of a model obtained on one set used for training is reproducible on others only to a limited extent. Moreover, benign traffic classes’ generalizability differs from harmful traffic. Given its application in the actual network environment, it implies that one needs to select the data used to train the ML model carefully to determine to what extent the classes present in the dataset used for training are similar to those in the real target traffic environment. On the other hand, merging datasets may result in more exhaustive data collection, consisting of a more diverse spectrum of training samples. Full article

Background/Objectives: Obstructive sleep apnea (OSA) is a highly prevalent disorder that significantly impacts quality of life and daily functioning. While continuous positive airway pressure (CPAP) therapy is effective, long-term adherence remains a challenge. This single-arm observational study aimed to evaluate clinical outcomes and adherence patterns during telemedicine-supported CPAP therapy and identify distinct phenotypic response clusters in Romanian patients with OSA. Methods: This prospective observational study included 86 adults diagnosed with OSA, treated with ResMed Auto CPAP devices at “Victor Babeș” University Hospital in Timișoara, Romania. All patients were remotely monitored via the AirView™ platform and received monthly telephone interventions to promote adherence when necessary. Clinical outcomes were assessed through objective telemonitoring data. K-means clustering and t-distributed stochastic neighbor embedding (t-SNE) were employed to explore phenotypic response patterns. Results: During telemedicine-supported CPAP therapy, significant clinical improvements were observed. The apnea–hypopnea index (AHI) decreased from 42.0 ± 21.1 to 1.9 ± 1.3 events/hour. CPAP adherence improved from 75.5% to 90.5% over six months. Average daily usage increased from 348.4 ± 85.8 to 384.2 ± 65.2 min. However, post hoc analysis revealed significant concerns about the validity of self-reported psychological improvements. Self-esteem changes showed negligible correlation with objective clinical measures (r < 0.2, all p > 0.1), with only 3.3% of variance being explained by measurable therapeutic factors (R² = 0.033). Clustering analysis identified four distinct adherence and outcome profiles, yet paradoxically, patients with lower adherence showed greater self-esteem improvements, contradicting therapeutic causation. Conclusions: Telemedicine-supported CPAP therapy with structured monthly interventions was associated with substantial clinical improvements, including excellent AHI reduction (22-fold) and high adherence rates (+15% after 6 months). Data-driven phenotyping successfully identified distinct patient response profiles, supporting personalized management approaches. However, the single-arm design prevents definitive attribution of improvements to telemonitoring versus natural adaptation or placebo effects. Self-reported psychological outcomes showed concerning patterns suggesting predominant placebo responses rather than therapeutic benefits. While the overall findings demonstrate the potential value of structured telemonitoring for objective CPAP outcomes, controlled trials are essential to establishing true therapeutic efficacy and distinguishing intervention effects from measurement bias. Full article

Background: Regulatory T cells (Tregs) are the main suppressor cells that maintain immune tolerance and prevent autoimmunity. Changes in Treg number or function are implicated in a wide range of autoimmune and inflammatory (AI/I) diseases, with or without underlying inborn errors of immunity (IEI). Understanding the phenotypic profiles of Treg subsets and their associations with immune dysregulation is crucial to identifying potential robust and holistic biomarkers for disease activity. Methods: We examined peripheral blood mononuclear cells from 40 patients diagnosed with various autoimmune/inflammatory diseases, including those with genetically confirmed inborn errors of immunity (IEIs), and compared these samples to those from 38 healthy controls of the same age. Utilizing multiparametric flow cytometry, we measured multiple Treg sub-populations and investigated their correlations with lymphocyte subset profiles and the diversity of autoantibodies. We applied advanced statistical and machine learning techniques, such as t-SNE, k-means clustering, and ROC analysis, to analyze immunophenotypic patterns in the patients. Results: Among all Treg sub-populations, only CD4⁺CD127^lowCD25^highFOXP3⁺ Tregs showed a significant decrease in patients compared to healthy controls (p < 0.05), while other Treg phenotypes did not differ. FOXP3 expression showed reduced intensity in patients and demonstrated diagnostic potential (AUC = 0.754). Notably, this Treg subset negatively correlated with CD19⁺ B cell percentages and positively correlated with the diversity of circulating autoantibodies. Unsupervised clustering revealed three distinct immunophenotypic profiles, highlighting heterogeneity among patients and underlining FOXP3-centered immune dysregulation. Conclusions: Our results presented that patients have an impairment in the CD4⁺CD127^lowCD25^highFOXP3⁺ regulatory T cell subset, which is identified by significantly decreased frequency and decreased expression of FOXP3. Immunological heterogeneity among patients was further uncovered by unsupervised clustering, highlighting the critical role that FOXP3-centered regulatory failure plays in the pathophysiology of illness. The combined evaluation of these three immunological factors, centered around FOXP3, holds promise as an integrative tool for monitoring disease progression across various autoimmune and immunodeficient contexts. Full article

In this paper, we calibrate the luminosity relation of gamma−ray bursts (GRBs) by employing artificial neural networks (ANNs) to analyze the Pantheon+ sample of type Ia supernovae (SNe Ia) in a manner independent of cosmological assumptions. The A219 GRB dataset is used to calibrate the Amati relation ($E_{\mathrm{p}}$-$E_{\mathrm{iso}}$) at low redshift with the ANN framework, facilitating the construction of the Hubble diagram at higher redshifts. Cosmological models are constrained with GRBs at high redshift and the latest observational Hubble data (OHD) via the Markov chain Monte Carlo numerical approach. For the Chevallier−Polarski−Linder (CPL) model within a flat universe, we obtain ${\Omega }_{\mathrm{m}}={0.321}_{-0.069}^{+0.078}$, $h={0.654}_{-0.071}^{+0.053}$, $w_0={-1.02}_{-0.50}^{+0.67}$, and $w_a={-0.98}_{-0.58}^{+0.58}$ at the 1 −$\sigma$ confidence level, which indicates a preference for dark energy with potential redshift evolution ($w_a\ne 0$). These findings using ANNs align closely with those derived from GRBs calibrated using Gaussian processes (GPs). Full article

Background: Leigh’s Disease is a rare mitochondrial disorder primarily affecting the central nervous system, with frequent secondary cardiac manifestations such as hypertrophic and dilated cardiomyopathies. Early detection of cardiac complications is crucial for patient management, but manual interpretation of cardiac MRI is labour-intensive and subject to inter-observer variability. Methodology: We propose an integrated deep learning framework using cardiac MRI to automate the detection of cardiac abnormalities associated with Leigh’s Disease. Four CNN architectures—Inceptionv3, a custom 3-layer CNN, DenseNet169, and EfficientNetB2—were trained on preprocessed MRI data (224 × 224 pixels), including left ventricular segmentation, contrast enhancement, and gamma correction. Morphological features (area, aspect ratio, and extent) were also extracted to aid interpretability. Results: EfficientNetB2 achieved the highest test accuracy (99.2%) and generalization performance, followed by DenseNet169 (98.4%), 3-layer CNN (95.6%), and InceptionV3 (94.2%). Statistical morphological analysis revealed significant differences in cardiac structure between Leigh’s and non-Leigh’s cases, particularly in area (212,097 vs. 2247 pixels) and extent (0.995 vs. 0.183). The framework was validated using ROC (AUC = 1.00), Brier Score (0.000), and cross-validation (mean sensitivity = 1.000, std = 0.000). Feature embedding visualisation using PCA, t-SNE, and UMAP confirmed class separability. Grad-CAM heatmaps localised relevant myocardial regions, supporting model interpretability. Conclusions: Our deep learning-based framework demonstrated high diagnostic accuracy and interpretability in detecting Leigh’s disease-related cardiac complications. Integrating morphological analysis and explainable AI provides a robust and scalable tool for early-stage detection and clinical decision support in rare diseases. Full article

Personality is a fundamental psychological trait that exerts a long-term influence on human behavior patterns and social interactions. Automatic personality recognition (APR) has exhibited increasing importance across various domains, including Human–Robot Interaction (HRI), personalized services, and psychological assessments. In this study, we propose a multimodal personality recognition model that classifies the Big Five personality traits by extracting features from three heterogeneous sources: audio processed using Wav2Vec2, video represented as Skeleton Landmark time series, and text encoded through Bidirectional Encoder Representations from Transformers (BERT) and Doc2Vec embeddings. Each modality is handled through an independent Self-Attention block that highlights salient temporal information, and these representations are then summarized and integrated using a late fusion approach to effectively reflect both the inter-modal complementarity and cross-modal interactions. Compared to traditional recurrent neural network (RNN)-based multimodal models and unimodal classifiers, the proposed model achieves an improvement of up to 12 percent in the F1-score. It also maintains a high prediction accuracy and robustness under limited input conditions. Furthermore, a visualization based on t-distributed Stochastic Neighbor Embedding (t-SNE) demonstrates clear distributional separation across the personality classes, enhancing the interpretability of the model and providing insights into the structural characteristics of its latent representations. To support real-time deployment, a lightweight thread-based processing architecture is implemented, ensuring computational efficiency. By leveraging deep learning-based feature extraction and the Self-Attention mechanism, we present a novel personality recognition framework that balances performance with interpretability. The proposed approach establishes a strong foundation for practical applications in HRI, counseling, education, and other interactive systems that require personalized adaptation. Full article

Background: Lokomat-assisted robotic rehabilitation is increasingly used for gait restoration in patients with spinal cord injury (SCI). However, the objective evaluation of treatment effectiveness through biomechanical parameters and machine learning approaches remains underexplored. Methods: This study analyzed data from 29 SCI patients undergoing Lokomat-based rehabilitation. A dataset of 46 variables including range of motion (L-ROM), joint stiffness (L-STIFF), and muscular force (L-FORCE) was examined using statistical methods (paired t-test, ANOVA, and ordinary least squares regression), clustering techniques (k-means), dimensionality reduction (t-SNE), and anomaly detection (Isolation Forest). Predictive modeling was applied to assess the influence of age, speed, body weight, body weight support, and exercise duration on biomechanical outcomes. Results: No statistically significant asymmetries were found between left and right limb measurements, indicating functional symmetry post-treatment (p > 0.05). Clustering analysis revealed a weak structure among patient groups (Silhouette score ≈ 0.31). Isolation Forest identified minimal anomalies in stiffness data, supporting treatment consistency. Regression models showed that body weight and body weight support significantly influenced joint stiffness (p < 0.01), explaining up to 60% of the variance in outcomes. Conclusions: Lokomat-assisted robotic rehabilitation demonstrates high functional symmetry and biomechanical consistency in SCI patients. Machine learning methods provided meaningful insight into the structure and predictability of outcomes, highlighting the clinical value of weight and support parameters in tailoring recovery protocols. Full article

To address the challenges of extracting rolling bearing degradation information and the insufficient performance of conventional convolutional networks, this paper proposes a rolling bearing degradation state identification method based on the improved monopulse feature extraction and a one-dimensional dilated residual convolutional neural network (1D-DRCNN). First, the fault pulse envelope waveform features are extracted through phase scanning and synchronous averaging, and a two-stage grid search strategy is employed to achieve FCC calibration. Subsequently, a 1D-DRCNN model is constructed to identify rolling bearing degradation states under different working conditions. The experimental study collects the vibration signals of nine degradation states, including the different sizes of inner and outer ring local faults as well as normal conditions, to comparatively analyze the proposed method’s rapid calibration capability and feature extraction quality. Furthermore, t-SNE visualization is utilized to analyze the network response to bearing degradation features. Finally, the degradation state identification performance across different network architectures is compared in pattern recognition experiments. The results show that the proposed improved feature extraction method significantly reduces the iterative calibration computational burden while effectively extracting local fault degradation information and overcoming complex working condition influence. The established 1D-DRCNN model integrates the advantages of dilated convolution and residual connections and can deeply mine sensitive features and accurately identify different bearing degradation states. The overall recognition accuracy can reach 97.33%. Full article

This study aims to rapidly in situ identify starch sausage samples with the improper addition of chicken bone paste. Chicken bones play important roles in building materials, biomass fuels, and as food additives after enzymatic hydrolysis, but no current research indicates that chicken bones can be directly added to food for consumption. Especially in starch sausages, the addition of chicken bone paste is highly controversial due to potential risks of esophageal laceration and religious concerns. This paper first uses laser-induced breakdown spectroscopy (LIBS) to investigate the elemental differences between starch sausages and chicken bone paste. By preparing mixtures of starch sausages and chicken bone paste at different ratios, the relationships between the spectral peak intensities of elements, such as Ca, Ba, and Sr, and the proportion of chicken bone paste were determined. Through processing methods such as normalization with reference spectral lines, selection of the signal of the second laser pulse at the same position, and electron temperature correction, the determination coefficients (R²) of each element’s spectral lines have significantly improved. Specifically, the R² values for Ca I, Ca II, Ba II, and Sr II have increased from 0.302, 0.694, 0.857, and 0.691 to 0.972, 0.952, 0.970, and 0.982, respectively. Finally, principal component analysis (PCA) was used to distinguish starch sausages, chicken bone paste, and their mixtures at different ratios, with further effective differentiation achieved through t-distributed stochastic neighbor embedding (t-SNE). The results show that LIBS technology can serve as an effective and rapid method for detecting elemental composition in food and distinguishing different food products, providing safety guarantees for food production and supervision. Full article

Accurate identification of electricity price anomalies is essential for enhancing transparency, stability, and efficiency in modern electricity markets. While prior methods primarily focus on temporal patterns, this study introduces a novel approach to detecting spatial anomalies by leveraging latent symmetry structures in nodal price data. The method consists of two key stages: (1) applying dimensionality reduction and density-based clustering (t-SNE + DBSCAN) to uncover symmetrical price zones, and (2) deploying the Isolation Forest algorithm to identify anomalous nodes and zones based on intra-zone and inter-zone data density deviations. Empirical tests on a full-year dataset from the PJM market (over 2000 nodes, 15 min intervals) show that the proposed method (M1) achieves a spatial anomaly detection accuracy above 95%, with false alarm rates consistently below 13%. Compared to benchmark models—including unzoned Isolation Forest (M2) and K-means-based methods (M3)—the proposed framework demonstrates superior stability and interpretability, especially in identifying clustered and zone-level anomalies linked to congestion or structural disturbances. By integrating spatial symmetry awareness into the detection framework, this approach enhances both sensitivity and traceability, enabling early-stage identification of systemic anomalies. The method is data-efficient and adaptable to diverse electricity market architectures. Overall, the proposed framework contributes a scalable and interpretable tool for anomaly surveillance in electricity markets, supporting more resilient and transparent market operations. Full article

Seismic waveform feature extraction is a critical task in seismic exploration, as it directly impacts reservoir prediction and geological interpretation. However, large-scale seismic data and nonlinear relationships between seismic signals and reservoir properties are challenging for traditional machine learning methods. To address these limitations, this paper proposes a novel framework combining Convolutional Neural Network (CNN) and Uniform Manifold Approximation and Projection (UMAP) for seismic waveform feature extraction and analysis. The UMAP-CNN framework leverages the strengths of manifold learning and deep learning, enabling multi-scale feature extraction and dimensionality reduction while preserving both local and global data structures. The evaluation experiments, which considered runtime, receiver operating characteristic (ROC) curves, embedding distribution maps, and other quantitative assessments, illustrated that the UMAP-CNN outperformed t-distributed stochastic neighbor embedding (t-SNE), locally linear embedding (LLE) and isometric feature mapping (Isomap). A case study in the Ordos Basin further demonstrated that UMAP-CNN offers a high degree of accuracy in predicting coal seam thickness. Furthermore, our framework exhibited superior computational efficiency and robustness in handling large-scale datasets. Full article

Aiming at tackling the challenges of traditional classification methods, which are labor-intensive, time-consuming, and inefficient, a nitrogen-efficient wheat variety classification method using support vector machine-extreme gradient boosting (SVM-XGBoost) based on unmanned aerial vehicle (UAV) hyperspectral remote sensing was proposed in this study. First, eight agronomic indicators closely related to wheat nitrogen efficiency were analyzed using t-SNE dimensionality reduction and hierarchical clustering, enabling the classification of 12 wheat varieties into nitrogen-efficient and nitrogen-inefficient varieties under different nitrogen stress conditions. Second, a hyperspectral feature band selection method based on least absolute shrinkage and selection operator-competitive adaptive reweighted sampling (Lasso-CARS) was employed using hyperspectral canopy data collected during the wheat heading stage with an UAV to extract feature bands relevant to nitrogen-efficient wheat classification. This approach aimed to mitigate the impact of high collinearity and noise in high-dimensional hyperspectral data on model construction. Furthermore, the SVM-XGBoost method integrated the extracted feature bands with the support vectors and decision function outputs from the preliminary SVM classification. It then leveraged XGBoost to capture nonlinear relationships and construct the final classification model using gradient-boosted trees, achieving intelligent classification of nitrogen-efficient wheat varieties. The model also selected nitrogen fertilization strategies based on the characteristics of different wheat varieties. The results demonstrated robust performance under low, high, and no nitrogen stress, with average overall accuracies of 74%, 83%, and 70% (Kappa coefficients: 0.67, 0.80, and 0.48), respectively. This study provided an efficient and accurate UAV hyperspectral remote sensing-based method for nitrogen-efficient wheat variety classification, offering a technological foundation to accelerate precision breeding. Full article

Traditional fault feature generation models often face issues of uncontrollability, singularity, and slow convergence, limiting diagnostic accuracy. To address these challenges, this paper proposes a symmetry-aware approach that combines a conditional variational autoencoder (CVAE) and an auxiliary classifier generative adversarial network (ACGAN) for fault feature generation, leveraging symmetry characteristics inherent in fault data distributions and adversarial learning. Specifically, symmetrical Gaussian distributions in the CVAE enable robust extraction of latent fault features conditioned on fault classes, which are then input to the symmetrical adversarial framework of the ACGAN to guide the generator and discriminator toward a symmetrical Nash equilibrium. The original and generated features are jointly utilized in a convolutional neural network (CNN) for fault classification. Experimental results on the CWRU dataset show that the proposed CVAE-ACGAN achieves an average accuracy of 99.21%, precision of 97.81%, and recall of 98.24%, surpassing the baseline CNN. Similar improvements are achieved on the PADERBORN dataset. Furthermore, the model achieves significantly lower root mean square error (RMSE) and mean absolute error (MAE) than competing methods, confirming high consistency between the generated and real features and supporting its superior generalization and reliability. Visualization via confusion matrices and t-SNE further demonstrates clear boundaries between fault categories. These results affirm the value of incorporating symmetry principles into feature generation for mechanical fault diagnosis. Full article

This study addresses the critical need for effective data fusion strategies in pest prediction for pitahaya (dragon fruit) cultivation in the Ecuadorian Amazon, where heterogeneous data sources—such as environmental sensors and chlorophyll measurements—offer complementary but fragmented insights. Current agricultural monitoring systems often fail to integrate these data streams, limiting early pest detection accuracy. To overcome this, we compared early and late fusion approaches using comprehensive experiments. Multidimensionality is a central challenge: the datasets span temporal (hourly sensor readings), spatial (plot-level chlorophyll samples), and spectral (chlorophyll reflectance) dimensions. We applied dimensionality reduction techniques—PCA, KPCA (linear, polynomial, RBF), t-SNE, and UMAP—to preserve relevant structure and enhance interpretability. Evaluation metrics included the proportion of information retained (score) and cluster separability (silhouette score). Our results demonstrate that early fusion yields superior integrated representations, with PCA and KPCA-linear achieving the highest scores (0.96 vs. 0.94), and KPCA-poly achieving the best cluster definition (silhouette: 0.32 vs. 0.31). Statistical validation using the Friedman test (${\chi }^2$ = 12.00, p = 0.02) and Nemenyi post hoc comparisons (p < 0.05) confirmed significant performance differences. KPCA-RBF performed poorly (score: 0.83; silhouette: 0.05), and although t-SNE and UMAP offered visual insights, they underperformed in clustering (silhouette < 0.12). These findings make three key contributions. First, early fusion better captures cross-domain interactions before dimensionality reduction, improving prediction robustness. Second, KPCA-poly offers an effective non-linear mapping suitable for tropical agroecosystem complexity. Third, our framework, when deployed in Joya de los Sachas, improved pest prediction accuracy by 12.60% over manual inspection, leading to more targeted pesticide use. This contributes to precision agriculture by providing low-cost, scalable strategies for smallholder farmers. Future work will explore hybrid fusion pipelines and sensor-agnostic models to extend generalizability. Full article