Search Results (12)

Sentiment analysis of online game reviews has increasingly become important in understanding player experiences and supporting data-driven game development. However, research in this domain has continuously faced two unresolved challenges: (1) the extreme imbalance between positive and negative feedback, and (2) the inefficiency of existing feature-weighting schemes in capturing sentiment signals embedded in informal gaming discourses. Prior works demonstrated that negative feedback—though a few in number are highly influential—usually contain richer emotional content and longer textual structures; yet, prevailing classification models often perform poorly for these minorities (i.e., negative feedback). Numerous studies explored multimodal imbalance issues, class imbalance in cross-lingual ABSA (Aspect-Based Sentiment Analysis), reinforcement-learning-based architectures for imbalanced extraction tasks, and oversampling strategies like SMOTE (Synthetic Minority Over-sampling Technique) variants. Few investigations specifically addressed imbalanced sentiment classification in the contexts of online game reviews, where user-generated content exhibits unique lexical, structural, and emotional characteristics. To address these gaps, this study integrated TF-IDF (Term Frequency-Inverse Document Frequency), VADER (Valence Aware Dictionary and Sentiment Reasoner) lexicon features, and IGM (Inverse Gravity Moment) weightings with advanced oversampling methods such as ADASYN (Adaptive Synthetic Sampling Approach for Imbalanced Learning) and Borderline-SMOTE to improve the detection of minority sentiment classes. Ensemble models, including XGBoost (Extreme Gradient Boosting) and LightGBM (Light Gradient-Boosting Machine), were further employed to enhance the robustness of imbalance. Using a large-scale dataset of Steam game reviews, the proposed framework demonstrated substantial improvement in identifying negative sentiments, addressing a critical limitation in the existing computational game-analysis literature, and advancing the modeling for detecting the emotion-rich but imbalance-prone user feedback. Full article

This study presents a machine learning framework for the reconstruction of fatigue life and fracture toughness in natural fiber-reinforced composites, evaluating the predictive accuracy of six regression algorithms—Random Forest, Gradient Boosting, Support Vector Machine, Neural Network, Ridge Regression, and Lasso Regression—using a controlled synthetic dataset of 600 samples generated from established Basquin fatigue and Rule of Mixtures fracture equations, incorporating stochastic noise calibrated to experimental scatter (CV = 15–50%), with log-normal noise standard deviation of 0.20 for fatigue life and Gaussian noise standard deviation of 0.15 for fracture toughness. The dataset encompasses eight natural fiber types (flax, jute, sisal, hemp, bamboo, coconut, banana, and pineapple) and five matrix systems (epoxy, polyester, PLA, vinyl ester, and polyurethane). Models were evaluated using a 70-15-15 train–validation–test split with 5-fold cross-validation and exhaustive grid search hyperparameter optimisation. Gradient Boosting achieved R² = 0.93 for fatigue life and Stacking Ensemble achieved R² = 0.87 for fracture toughness, representing 97% and 89% of their respective noise-ceiling values (theoretical maximum R² of 0.96 and 0.98 given the programmed noise levels). The ML models perform supervised function approximation—learning to reconstruct the programmed generation equations rather than discovering novel physical composite behaviour—and function as automated surrogates for the governing equations. Feature importance analysis identified engineered composite indicators, stress amplitude, and fiber length as the most influential parameters. The framework provides a reproducible ML evaluation pipeline as a methodological template for future experimental composite studies. Full article

Accurate prediction of landslide displacement is crucial for hazard prevention. However, recurrent neural network (RNN) models have limitations in simultaneously capturing lag time and feature importance, and their black-box nature limits their interpretability. Moreover, the performance of single models varies across different deformation stages, especially during acceleration. To address these challenges, we propose an interpretable deep reinforcement learning-based adaptive ensemble (DRL-AE) framework. The method employs Seasonal and Trend decomposition using Loess to separate cumulative displacement into trend and periodic components. Trend and periodic sequences are predicted using double exponential smoothing and three RNN variants, respectively. An improved Convolutional Block Attention Module (ICBAM) enhances periodic feature extraction and provides temporal–spatial interpretability. The Deep Deterministic Policy Gradient algorithm adaptively integrates multi-model predictions in response to evolving environmental conditions. To validate the DRL-AE, a case study is conducted on the Baijiabao landslide in Zigui County, China. The results indicate that the DRL-AE substantially enhances prediction accuracy. For periodic displacement, it reduces MAE by 10.02% and RMSE by 6.65%, and increases R² by 4.27% compared with the ICBAM-GRU model. The results also confirm the effectiveness of ICBAM in feature extraction, and the generated heatmaps provide intuitive interpretability of the relevant triggering factors. Full article

Accurate prediction of wear behavior in polymer nanocomposites remains challenging due to the coupled influence of operating conditions and evolving surface morphology. In this study, a surface-aware triboinformatics framework is proposed to predict the dry sliding wear behavior of multi-walled carbon nanotube (MWCNT) reinforced epoxy composites by integrating operating parameters with run-wise atomic force microscopy (AFM) surface descriptors. Wear experiments were conducted using a Taguchi L16 design by varying CNT content (0–0.75 wt.%), applied load (10–40 N), sliding speed (183–458 rpm), and sliding distance (500–1250 m). AFM-derived parameters, including Ra, Rq, Z-range, and surface area difference, were extracted from the worn surface corresponding to each experimental run. Multiple regression-based machine learning models were evaluated using leave-one-out cross-validation, with ensemble-based models providing the best predictive performance (R² > 0.85 with low RMSE and MAE). Feature importance and partial dependence analyses identified CNT content as the dominant factor controlling wear reduction, followed by Z-range and Ra, highlighting the critical role of surface damage severity. Neat epoxy exhibited a maximum wear loss of 0.444 mg, whereas the 0.75 wt.% CNT composite showed values as low as 0.003 mg under comparable conditions, corresponding to a reduction of approximately 99%. The proposed framework enables mechanistically interpretable wear prediction and supports the design of durable polymer composites, contributing to SDG 9 (Industry, Innovation and Infrastructure) and SDG 12 (Responsible Consumption and Production). Full article

No-reference stereoscopic image quality assessment (NR-SIQA) remains a fundamental challenge due to the complex biological mechanisms of binocular rivalry and fusion, particularly under asymmetric distortions. In this paper, we propose a novel framework termed Multi-Stage Complementary Ensemble (MSCE). The core innovation lies in the Adaptive Selective Propagation (ASP) strategy embedded within a hierarchical Transformer architecture to dynamically regulates the fusion of binocular features. Specifically, by simulating the human visual system’s transition from binocular rivalry to fusion, the ASP strategy applies nonlinear gain control to selectively reinforce features from the governing view based on binocular discrepancies. Furthermore, the proposed Hierarchical Complementary Fusion (HCF) module effectively captures and integrates low-level texture integrity, mid-level structural degradation, and high-level semantic consistency, leveraging ensemble learning principles, within a unified quality-aware manifold. Experimental results on four benchmark datasets demonstrate that the MSCE framework achieves state-of-the-art performance, particularly in terms of prediction consistency under complex asymmetric distortions. Full article

Background/Objectives: Accurate classification of brain tumors and reliable prediction of patient survival are essential in neuro-oncology, guiding clinical decisions and enabling precision treatment planning. However, conventional machine learning and deep learning methods often struggle with challenges such as data scarcity, class imbalance, limited model interpretability, and poor generalization across diverse clinical settings. This study presents GlioSurvQNet, a novel reinforcement learning-based framework designed to address these limitations for both glioma grading and survival prediction. Methods: GlioSurvQNet is built upon a DuelContextAttn Deep Q-Network (DQN) architecture, tailored for binary classification of low-grade vs. high-grade gliomas and multi-class survival prediction (short-, medium-, and long-term categories). Radiomics features were extracted from multimodal MRI scans, including FLAIR, T1CE, and T2 sequences. Feature optimization was performed using a hybrid ensemble of metaheuristic algorithms, including Harris Hawks Optimization (HHO), Modified Gorilla Troops Optimization (mGTO), and Zebra Optimization Algorithm (ZOA). Subsequently, SHAP-based feature selection was applied to enhance model interpretability and robustness. Results: The classification module achieved the highest accuracy of 99.27% using the FLAIR + T1CE modality pair, while the survival prediction model attained an accuracy of 93.82% with the FLAIR + T2 + T1CE fusion. Comparative evaluations against established machine learning and deep learning models demonstrated that GlioSurvQNet consistently outperformed existing approaches in both tasks. Conclusions: GlioSurvQNet offers a powerful and interpretable AI-driven solution for brain tumor analysis. Its high accuracy and robustness make it a promising tool for clinical decision support in glioma diagnosis and prognosis. Full article

Owing to its excellent crack resistance and durability, High-Performance Fiber-Reinforced Concrete (HPFRC) has been extensively applied in engineering structures exposed to extreme loading conditions. The Mode I dynamic fracture strength of HPFRC under high-strain-rate conditions exhibits significant strain-rate sensitivity and nonlinear response characteristics. However, existing experimental methods for strength measurement are limited by high costs and the absence of standardized testing protocols. Meanwhile, conventional data-driven models for strength prediction struggle to achieve both high-precision prediction and physical interpretability. To address this, this study introduces a dynamic fracture strength prediction method based on a feature-weighted linear ensemble (FWL) mechanism. A comprehensive database comprising 161 sets of high-strain-rate test data on HPFRC fracture strength was first constructed. Key modeling variables were then identified through correlation analysis and an error-driven feature selection approach. Subsequently, six representative machine learning models (KNN, RF, SVR, LGBM, XGBoost, MLPNN) were employed as base learners to construct two types of ensemble models, FWL and Voting, enabling a systematic comparison of their performance. Finally, the predictive mechanisms of the models were analyzed for interpretability at both global and local scales using SHAP (SHapley Additive exPlanations) and LIME (Local Interpretable Model-agnostic Explanations) methods. The results demonstrate that the FWL model achieved optimal predictive performance on the test set (R² = 0.908, RMSE = 2.632), significantly outperforming both individual models and the conventional ensemble method. Interpretability analysis revealed that strain rate and fiber volume fraction are the primary factors influencing dynamic fracture strength, with strain rate demonstrating a highly nonlinear response mechanism across different ranges. The integrated prediction framework developed in this study offers the combined advantages of high accuracy, robustness, and interpretability, providing a novel and effective approach for predicting the fracture behavior of HPFRC under high-strain-rate conditions. Full article

Diabetic retinopathy (DR), a leading cause of vision loss worldwide, poses a critical challenge to healthcare systems due to its silent progression and the reliance on labor-intensive, subjective manual screening by ophthalmologists, especially amid a global shortage of eye care specialists. Addressing the pressing need for scalable, objective, and interpretable diagnostic tools, this work introduces RetinoDeep—deep learning frameworks integrating hybrid architectures and explainable AI to enhance the automated detection and classification of DR across seven severity levels. Specifically, we propose four novel models: an EfficientNetB0 combined with an SPCL transformer for robust global feature extraction; a ResNet50 ensembled with Bi-LSTM to synergize spatial and sequential learning; a Bi-LSTM optimized through genetic algorithms for hyperparameter tuning; and a Bi-LSTM with SHAP explainability to enhance model transparency and clinical trustworthiness. The models were trained and evaluated on a curated dataset of 757 retinal fundus images, augmented to improve generalization, and benchmarked against state-of-the-art baselines (including EfficientNetB0, Hybrid Bi-LSTM with EfficientNetB0, Hybrid Bi-GRU with EfficientNetB0, ResNet with filter enhancements, Bi-LSTM optimized using Random Search Algorithm (RSA), Particle Swarm Optimization (PSO), Ant Colony Optimization (ACO), and a standard Convolutional Neural Network (CNN)), using metrics such as accuracy, F1-score, and precision. Notably, the Bi-LSTM with Particle Swarm Optimization (PSO) outperformed other configurations, achieving superior stability and generalization, while SHAP visualizations confirmed alignment between learned features and key retinal biomarkers, reinforcing the system’s interpretability. By combining cutting-edge neural architectures, advanced optimization, and explainable AI, this work sets a new standard for DR screening systems, promising not only improved diagnostic performance but also potential integration into real-world clinical workflows. Full article

This paper proposes a novel navigation approach for Unmanned Tracked Vehicles (UTVs) using prior-based ensemble deep reinforcement learning, which fuses the policy of the ensemble Deep Reinforcement Learning (DRL) and Dynamic Window Approach (DWA) to enhance both exploration efficiency and deployment safety in unstructured off-road environments. First, by integrating kinematic analysis, we introduce a novel state and an action space that account for rugged terrain features and track–ground interactions. Local elevation information and vehicle pose changes over consecutive time steps are used as inputs to the DRL model, enabling the UTVs to implicitly learn policies for safe navigation in complex terrains while minimizing the impact of slipping disturbances. Then, we introduce an ensemble Soft Actor–Critic (SAC) learning framework, which introduces the DWA as a behavioral prior, referred to as the SAC-based Hybrid Policy (SAC-HP). Ensemble SAC uses multiple policy networks to effectively reduce the variance of DRL outputs. We combine the DRL actions with the DWA method by reconstructing the hybrid Gaussian distribution of both. Experimental results indicate that the proposed SAC-HP converges faster than traditional SAC models, which enables efficient large-scale navigation tasks. Additionally, a penalty term in the reward function about energy optimization is proposed to reduce velocity oscillations, ensuring fast convergence and smooth robot movement. Scenarios with obstacles and rugged terrain have been considered to prove the SAC-HP’s efficiency, robustness, and smoothness when compared with the state of the art. Full article

Bond behavior between steel bars and concrete is fundamental to the structural integrity and durability of reinforced concrete. However, corrosion-induced deterioration severely impairs bond performance, highlighting the need for advanced and reliable assessment methods. This paper pioneers an algorithm for an advanced ensemble learning framework to predict bond strength between corroded steel bars and concrete. In this framework, a novel Stacked Boosted Bond Model (SBBM) is developed, in which a Fusion-Based Feature Selection (FBFS) strategy is integrated to optimize input variables, and SHapley Additive exPlanations (SHAP) are employed to enhance interpretability. A merit of the framework is that it can effectively identify critical factors such as crack width, transverse confinement, and corrosion level, which have often been neglected by traditional models. The proposed SBBM achieves superior predictive performance, with a coefficient of determination (R²) of 0.94 and a mean absolute error (MAE) of 1.33 MPa. Compared to traditional machine learning and analytical models, it demonstrates enhanced accuracy, generalization, and interpretability. This paper provides a reliable and transparent tool for structural performance evaluation, service life prediction, and the design of strengthening measures for corroded reinforced concrete structures, contributing to safer and more durable concrete structures. Full article

This paper investigates the application of artificial intelligence (AI) in forecasting Saudi Arabia’s non-oil export trajectories, contributing to the Kingdom’s Vision 2030 objectives for economic diversification. A suite of machine learning models, including LSTM, Transformer variants, Ensemble Stacking, XGBRegressor, and Random Forest, was applied to historical export and GDP data. Among them, the Advanced Transformer model, configured with an increased attention head size, achieved the highest accuracy (MAPE: 0.73%), effectively capturing complex temporal dependencies. The Non-Linear Blending Ensemble, integrating Random Forest, XGBRegressor, and AdaBoost, also performed robustly (MAPE: 1.23%), demonstrating the benefit of leveraging heterogeneous learners. While the Temporal Fusion Transformer (TFT) provided a useful macroeconomic context through GDP integration, its relatively higher error (MAPE: 5.48%) highlighted the challenges of incorporating aggregate indicators into forecasting pipelines. Explainable AI tools, including SHAP analysis and Partial Dependence Plots (PDPs), revealed that recent export lags (lag1, lag2, lag3, and lag10) were the most influential features, offering critical transparency into model behavior. These findings reinforce the promise of interpretable AI-powered forecasting frameworks in delivering actionable, data-informed insights to support strategic economic planning. Full article

Near-global Digital Elevation Model (DEM) products generated through space-based radar techniques have become a basic data source for a variety range of applications. However, these DEM products often contain typical errors such as vegetation bias and topography-related errors, which impede their practical utility. Despite the development of numerous correction methods based on mathematical fitting and artificial neural networks over recent decades, reliably correcting large-scale spaceborne radar-derived DEMs remains an open challenge due to issues like underfitting or overfitting. This paper introduces a novel framework called Feature-Reinforced Ensemble Learning (FREEL) designed specifically for correcting space-based radar-derived DEMs. Within this FREEL framework, a feature derivation module and a feature reinforcement module are integrated to enhance the original input features. Subsequently, an adaptive weighting variant of the DeepForest algorithm is proposed to emphasize critical features and improve training robustness, even with limited training data. The Shuttle Radar Topographic Mission (SRTM) DEMs of Hunan Province, China, characterized by diverse surface terrain and vegetation coverage, were selected to evaluate the FREEL framework. The results indicate that the accuracy of the SRTM DEM corrected using the FREEL framework improved by 40%, surpassing several mathematical fitting and machine learning baseline algorithms by an average of 45% and 23%, respectively. This method provides a more robust solution for correcting near-global space-based radar-derived DEM products. Full article