Search Results (112)

CO₂ adsorption on subnanometric metal clusters is highly sensitive to the computational protocol used to describe the potential energy surface, particularly when several low-lying geometries and spin states are accessible. In this work, CO₂ adsorption on Cu₄ and Sc₄ clusters was investigated using density functional theory (DFT) to evaluate how the choice of functional/basis-set protocol, spin multiplicity, initial geometry, and vibrational stability affects the predicted adsorption behavior. Four representative computational protocols (TPSSh, r²SCAN-3c, PBE-D4/def2-TZVP, and PBE0-SDD) were assessed for isolated clusters and cluster–CO₂ complexes. The lowest harmonic vibrational frequency, ω_min, was used as a diagnostic criterion to distinguish true minima from unstable or weakly defined stationary points. Selected cases were also cross-checked using the ORCA and Gaussian quantum-chemistry packages to assess whether comparable computational settings yielded consistent stationary-point character. The results show that Cu₄ generally exhibits weak CO₂ binding, whereas Sc₄ displays stronger but more protocol-dependent adsorption, consistent with its higher structural flexibility and more pronounced Lewis-acid character. Low-frequency and imaginary modes were found in several optimized structures, indicating that adsorption energies should not be interpreted without prior vibrational validation. The comparison also shows that variations in functional/basis-set treatment and spin multiplicity can alter both the optimized geometry and the predicted adsorption strength. Therefore, CO₂ adsorption on small metal clusters should be discussed using combined structural, vibrational, and energetic criteria rather than electronic adsorption energies alone. Overall, this study provides a protocol-oriented framework for evaluating the reliability of DFT predictions in CO₂ adsorption on Cu₄ and Sc₄ clusters. Full article

Pure electric construction machinery (PECM) is gradually becoming the mainstream choice for industrial construction. This paper presents a new configuration of an integrated charger for PECM. The proposed configuration employs a nine-switch-converter (NSC) that can achieve charging and traction functions for the target application. In charging mode, the motor is reused as a filter inductor and the NSC is reused as a conventional three-phase PWM rectifier. Data-driven adaptive predictive control (DAPC) based on recursive least squares (RLS) is proposed to cope with the motor’s saturation problem in charging mode. This control has the advantages of excellent robustness and fast dynamic response. Although the initial parameters are derived from the system model in the first sampling cycle, the controller subsequently relies entirely on online identification, which significantly reduces the sensitivity to parameter accuracy and eliminates the need for manual tuning of controller gains. In propulsion mode, the NSC enables independent operation of the two motors. The proposed configuration improves the utilization of devices and motors, which greatly reduces the weight, volume, and cost of the charger. Finally, an experimental platform was built to verify the feasibility and validity of the proposed topology and control algorithm. Full article

This study investigated the influence of hyperparameter selection within an EEMD–AR–SVM framework for bearing fault diagnosis under constant- and variable-speed operating conditions. Two preprocessing configurations, namely, Method 1, in which EEMD was applied after segmentation, and Method 2, in which EEMD preceded segmentation, were evaluated under three rotational regimes—constant speed, acceleration (Test A), and deceleration (Test B)—while number of Intrinsic Mode Functions (N), autoregressive model order (L), and segment length were systematically varied towards identifying combinations that maximized classification accuracy. The results showed the methods achieved 100% accuracy under constant-speed operation. However, Method 2 consistently outperformed Method 1 under nonstationary regimes, reaching 94.12% accuracy during acceleration and 95.00% during deceleration. The outer race remained the most challenging fault type, although its separability substantially improved when EEMD was performed prior to segmentation. The findings demonstrated, in a clear and interpretable manner, that the empirical choice of N and L directly affects classifier accuracy in stationary and nonstationary scenarios and the order of preprocessing steps plays a decisive role in diagnostic reliability. Such contributions provide a reproducible methodological basis for advancing vibration-based fault diagnosis and support the development of interpretable, high-performance predictive maintenance strategies for industrial environments. Full article

New energy power generation has become the first choice for low-carbon reform in the energy industry due to its emission reduction characteristics and environmental friendliness. However, due to the fluctuating nature of renewable energy, sustaining consistent reliability and secure performance within the power network has become increasingly challenging. A novel ensemble prediction scheme for photovoltaic (PV) output is presented, leveraging multi-source environmental data fusion to enhance forecast precision. The relationship between environmental variables and PV generation is quantitatively assessed using Pearson’s correlation coefficient to isolate the most influential factors. Subsequently, the PV time-series data are decomposed via variational mode decomposition (VMD) to extract multi-scale dynamic patterns. The refined features are then utilized within a long short-term memory (LSTM) network, whose parameters are adaptively optimized by the zebra optimization algorithm (ZOA). Historical datasets comprising environmental observations and corresponding PV generation records from a representative power station serve as the empirical basis. Results reveal that the VMD-ZOA-LSTM framework achieves the lowest RMSE and MAE, reducing errors by over 50% relative to comparative models. Furthermore, its R² metric outperforms that of the baseline LSTM and VMD-LSTM configurations by 2.05% and 1.19%, respectively, thereby substantiating the efficiency and validity of the proposed modeling strategy. Full article

Background/Objectives: Predicting individual response to depression therapy prior to treatment initiation remains a critical clinical challenge, as the response rate to both selective serotonin reuptake inhibitors (SSRIs) and repetitive transcranial magnetic stimulation (rTMS) is approximately 50%, leaving treatment selection largely trial-based. This study presents a computer-aided decision (CAD) framework that predicts depression therapy outcomes from pre-treatment electroencephalogram (EEG) signals using advanced time-frequency representations and pretrained convolutional neural networks (CNNs). Methods: EEG signals from 30 SSRI patients and 46 rTMS patients are transformed into time-frequency images using Continuous Wavelet Transform (CWT), Variational Mode Decomposition (VMD), and their pixel-level fusion. Four pretrained CNN architectures, including ResNet-18, MobileNet-V3, EfficientNet-B0, and TinyViT-Hybrid, are fine-tuned and evaluated under both image-independent and subject-independent 6-fold cross-validation (CV). Results: Results reveal a clear therapy-specific pattern: CWT-based representations yield superior discrimination for SSRI outcome prediction, with ResNet-18 achieving 99.43% image-level accuracy, while VMD-based representations are statistically superior for rTMS outcome prediction, with ResNet-18 reaching 98.77%. Pixel-level fusion of CWT and VMD does not consistently improve performance over the best individual representation in either therapy context. Pairwise Wilcoxon signed-rank tests confirm a two-tier architectural hierarchy in which ResNet-18 and TinyViT-Hybrid significantly outperform MobileNet-V3 and EfficientNet-B0 across all conditions, while remaining statistically indistinguishable from each other. At the subject level, the framework achieves 82.50% and 83.53% accuracy for SSRI and rTMS, respectively, under strict subject-independent evaluation. Per-channel analysis reveals occipital dominance for SSRI under CWT and frontotemporal dominance for rTMS under VMD, consistent with known neurophysiological mechanisms. Conclusions: These findings demonstrate that the choice of time-frequency representation is therapy-specific and at least as important as architectural complexity, and that competitive performance can be achieved without recurrent or attention layers by combining well-designed spectral images with a simple pretrained residual network. Full article

Delays caused by motor vehicle traffic, accidents, and environmental pollution present considerable challenges to sustainable urban mobility. To address these issues, transportation system users are encouraged to adopt active transportation methods, micromobility options, and public transit. Electric scooters have become a notably popular micromobility choice, especially following the emergence of vehicle-sharing companies in 2018, a trend that gained further momentum during the COVID-19 pandemic. This study explored the demographic characteristics, attitudes, and behaviors of e-scooter users in Istanbul through an online survey conducted from 1 September 2023 to 1 May 2024. A total of 462 e-scooter users participated, providing valuable insights into their preferred modes of transportation across 24 different scenarios specifically designed for this research. The responses were analyzed using various machine learning techniques, including Artificial Neural Networks, Decision Trees, Random Forest, and Gradient Boosting methods. Among the models developed, the Decision Tree model exhibited the highest overall performance, demonstrating strong accuracy and predictive capabilities across all classifications. Notably, all models significantly surpassed the accuracy of discrete choice models reported in existing literature, underscoring the effectiveness of machine learning approaches in modeling transportation mode choices. The models created in this study can serve various purposes for researchers, central and local authorities, as well as e-scooter service providers, supporting their strategic and operational decision-making processes. Future research could explore different machine learning methodologies to create a model that more accurately reflects individual preferences across diverse urban environments. These models can assist in developing sustainable mobility policies and reducing the environmental footprint of urban transportation systems. Full article

The Electric Vehicle (EV) industry is developing rapidly, and EVs are becoming an increasingly important choice for the future of transportation. Therefore, accurately forecasting the electricity demand for EVs is crucial. This paper presents a hybrid deep learning model for EV charging load prediction based on Multivariate Variational Mode Decomposition (MVMD), Improved Artemisinin Optimization algorithm (IAO), and Deep Representation Learning Extreme Learning Machines (DrELMs). Firstly, MVMD decomposes the original data into several modal components. Secondly, IAO optimizes the hyperparameters of the DrELM model. Finally, the trained IAO-DrELM model predicts multiple modal components following MVMD decomposition to obtain the final predictions. Experimental results show that the proposed model outperforms eight other models, achieving the lowest Mean Squared Error (MSE), Root Mean Squared Error (RMSE), and Mean Absolute Error (MAE) error values and the highest Coefficient of Determination (R²) value. Full article

Objectives: Grounded in Zimbardo’s Time Perspective theory and Regulatory Mode theory, together with developmental accounts of adolescent prospection and value-based choice, this study tests a unified model in which Locomotion (primary) and Future time perspective (secondary) jointly predict Anticipatory Pleasure in adolescence, while considering Assessment, gender, age, and sensation seeking. The goal is to understand how adolescents’ temporal orientation and self-regulation contribute to their motivational and hedonic functioning. Methods: A total of 1540 adolescents (aged 14–19 years) completed validated self-report measures assessing time perspective, regulatory mode (assessment and locomotion), anticipatory and consummatory pleasure, and sensation seeking. Gender differences were examined with independent-samples t-tests, while associations among variables were tested using Pearson correlations and hierarchical regression analyses. Results: Female adolescents reported significantly higher levels of future orientation and anticipatory pleasure, while males showed greater sensation seeking. Future time perspective and locomotion were positively correlated with anticipatory pleasure. In the regression analysis, locomotion emerged as the strongest predictor of anticipatory pleasure, followed by future orientation. Sensation seeking was not a significant predictor. Conclusions: The findings underscore the importance of future-oriented thinking and action-driven self-regulation in sustaining adolescents’ capacity to anticipate and derive motivation from future experiences. Gender-based motivational pathways are also highlighted, suggesting the need for differentiated developmental interventions. The study provides new insights into the interplay between time-based cognition and motivational dynamics during adolescence. Full article

Background: Exposure therapy is an established intervention for treating specific phobias. This study evaluates a Virtual Exposure Therapist (VET), a virtual reality (VR)-based system enhanced with artificial intelligence (AI), designed to reduce spider fear symptoms. Methods: The VET system delivers three progressive exposure scenarios involving interactive 3D spider models and features an adaptive relaxation mode triggered when physiological stress exceeds preset thresholds. AI integration is rule-based, enabling real-time adjustments based on session duration, head movement (degrees/s), and average heart rate (bpm). Fifty-five participants (aged 18–35) with self-reported moderate to high fear of spiders completed seven sessions using the VET system. Participants were not clinically diagnosed, which limits the generalizability of findings to clinical populations. Ethical approval was obtained, and informed consent was secured. Behavioral responses were analyzed using AR(p)–GARCH (1,1) models to account for intra-session volatility in anxiety-related indicators. The presence of ARCH effects was confirmed through the Lagrange Multiplier test, validating the model choice. Results: Results demonstrated a 21.4% reduction in completion time and a 16.7% decrease in average heart rate across sessions. Head movement variability declined, indicating increased user composure. These changes suggest a trend toward reduced phobic response over repeated exposures. Conclusions: While findings support the potential of AI-assisted VR exposure therapy, they remain preliminary due to the non-clinical sample and absence of a control group. Findings indicate expected symptom improvement across sessions; additionally, within-session volatility metrics (persistence/half-life) provided incremental predictive information about later change beyond session means, with results replicated using simple volatility proxies. These process measures are offered as complements to standard analyses, not replacements. Full article

Parking shortages and high costs in Chinese central business districts (CBDs) remain major urban challenges. Emerging automated vehicles (AVs) are expected to diversify parking options and mitigate these problems. However, AV users’ parking preferences and their influencing factors within existing urban zoning frameworks remain unclear. This study examines Nanjing as a representative case, proposing six distinct AV parking modes. Using survey data from 4644 responses collected from 1634 potential users, we employed nested logit models and random forest algorithms to analyze parking choice behavior. Results indicate that diversified AV parking modes would significantly reduce CBD parking demand. Users with medium- to long-term needs prefer home-parking, while short-term users favor CBD proximity. Key influencing factors include parking service satisfaction, duration, congestion time, AV punctuality, and individual characteristics, with satisfaction attributes showing the greatest impact across all modes. Comparative analysis reveals that random forest algorithms provide superior predictive accuracy for parking mode importance, while nested logit models better explain causal relationships between choices and influencing factors. This study establishes a dual analytical framework combining interpretability and predictive accuracy for urban AV parking research, providing valuable insights for transportation management and future metropolitan studies. Full article

This study introduces a data-driven twin modeling framework based on modern Koopman operator theory, offering a significant advancement over classical modal decomposition by accurately capturing nonlinear dynamics with reduced complexity and no manual parameter adjustment. The method integrates a novel algorithm with Pareto front analysis to construct a compact, high-fidelity reduced-order model that balances accuracy and efficiency. An explainable NLARX deep learning framework enables real-time, adaptive calibration and prediction, while a key innovation—computing orthogonal Koopman modes via randomized orthogonal projections—ensures optimal data representation. This approach for data-driven twin modeling is fully self-consistent, avoiding heuristic choices and enhancing interpretability through integrated explainable learning techniques. The proposed method is demonstrated on shock wave phenomena using three experiments of increasing complexity accompanied by a qualitative analysis of the resulting data-driven twin models. Full article

To investigate the oscillation modes of iced transmission lines, this study introduces a forcing term into the galloping equation and applies two discretization approaches: Discrete Method I (DMI), which directly transforms the partial differential equation into an ordinary differential form, and Discrete Method II (DMII), which first averages dynamic tension along the span. The finite element method is employed to validate the analytical solutions. Using a multiscale approach, amplitude-frequency responses under primary, harmonic, and internal resonance are derived. Results show that DMII yields larger galloping amplitudes and trajectories than DMI, with lower resonant frequencies and weaker geometric nonlinearities. In harmonic resonance, superharmonic and subharmonic modes (notably 1/2) are more easily excited. Under 2:1:2 internal resonance, amplitude differences in the vertical (z) direction are more sensitive to the discretization method, whereas the 1:1:1 case shows minimal variation across directions. These findings suggest that the choice of discretization significantly influences galloping behavior, with DMII offering a more conservative prediction. Full article

This study examines travel mode choice behavior within the context of Thailand’s emerging high-speed rail (HSR) development. It conducts a comparative assessment of predictive capabilities between the conventional Multinomial Logit (MNL) framework and advanced data-driven methodologies, including gradient boosting algorithms (Extreme Gradient Boosting, Light Gradient Boosting Machine, Categorical Boosting) and neural network architectures (Deep Neural Network, Convolutional Neural Network). The analysis leverages stated preference (SP) data and employs Bayesian optimization in conjunction with a stratified 10-fold cross-validation scheme to ensure model robustness. CatBoost emerges as the top-performing model (area under the curve = 0.9113; accuracy = 0.7557), highlighting travel cost, service frequency, and waiting time as the most influential determinants. These findings underscore the effectiveness of machine learning approaches in capturing complex behavioral patterns, providing empirical evidence to guide high-speed rail policy development in low- and middle-income countries. Practical implications include optimizing fare structures, enhancing service quality, and improving station accessibility to support sustainable adoption. Full article

Individual mobility behavior continues to pose a challenge to achieving climate goals, as motorized individual transportation is still favored over public transportation. The present study examines five possible drivers of more sustainable transportation mode choices: two infrastructural factors, specifically city center accessibility and railway accessibility, and three psychological variables: adaptability, climate change perception, and car orientation. A sample of N = 187 participants was collected in a German city in the Lower Rhine region. Our findings, based on ordinal logistic regression models, indicate that railway accessibility and car orientation are associated with both the use of motorized and public transportation. While center accessibility and adaptability predicted the use of motorized individual transportation, these variables did not significantly relate to the use of public transportation. Also, our results indicate that climate change perception does not relate to transportation use. This surprising finding is discussed in detail. On a more general level, the study’s insights reinforce previous findings and stress the importance of considering not only infrastructural factors in urban spaces but also the characteristics and attitudes of their inhabitants. Full article

Predicting and analyzing travel mode choices and purposes are significant to improve urban travel mobility and transportation planning. Previous research has ignored the interconnection between travel mode choices and purposes and thus overlooked their potential contributions to predictions. Using individual travel chain data collected in South Korea, this study proposes a Multi-Task Learning Deep Neural Network (MTLDNN) framework, integrating RFM (Recency, Frequency, Monetary) to achieve a joint prediction of travel mode choices and purposes. The MTLDNN is constructed to share a common hidden layer that extracts general features from the input data, while task-specific output layers are dedicated to predicting travel modes and purposes separately. This structure allows for efficient learning of shared representations while maintaining the capacity to model task-specific relationships. RFM is then integrated to optimize the extraction of users’ behavioral features, which helps in better understanding the temporal and financial patterns of users’ travel activities. The results show that the MTLDNN demonstrates consistent input variable replacement modes and selection probabilities in generating behavioral replacement patterns. Compared to the multinomial logit model (MNL), the MTLDNN achieves lower cross-entropy loss and higher prediction accuracy. The proposed framework could enhance transportation planning, efficiency, and user satisfaction by enabling more accurate predictions. Full article