Search Results (1,476)

In this work, we inspected the friendship network on Twitter (recently rebranded as X), concentrating on individuals and organizations intertwined with the energy field. We particularly focus on seasoned professionals, corporate entities, and domain specialists, all connected through ‘following’ relationships. By meticulously examining these ties, we uncover several distinct groupings within the network, each defined by the unique roles its members occupy. Our analysis demonstrates that the natural emergence of such clusters on social platforms exerts a profound influence on public discourse regarding energy and other critical matters, including climate change. Furthermore, we observe that the resulting communities exhibit distinct structural properties and communication patterns, with some clusters showing lower internal engagement, which may be indicative of fragmentation dynamics in online conversations. These emergent clusters, characterized by their shared communication styles, form relatively compact communities where the exchange of information is infrequent compared to larger networks and is usually confined to accounts created for specific commercial objectives. We emphasize that our analysis focuses on a structurally coherent connected component emerging from a curated set of energy-related seed accounts, rather than attempting to reconstruct the entirety of the energy discourse on Twitter. Consequently, peripheral or weakly connected communities may be underrepresented. Additionally, by combining machine-learning-based node classification with graph-based centrality measures, we are able to characterize the roles of structurally central actors within these niche segments and analyze the connectivity patterns that define their positions. This method provides novel insights into how corporate communication unfolds on social media, offering a refreshed perspective on professional networking. Ultimately, our findings highlight the ways in which companies within the energy sector take advantage of Twitter to coordinate their initiatives, with key institutions serving as central nodes in maintaining the organization of these networks. Full article

Despite the growing popularity of digital payment methods and online shopping environments, little is known about the psychological mechanisms through which they affect consumer buying patterns. Drawing on the Stimulus–Organism–Response (SOR) framework, this study introduces the concept of spendception and examines its dual dimensions: perceived spendception ease (PSE) and perceived spendception control (PSC). These dimensions serve as mechanisms linking digital twin environments (DTEs) to impulse buying. Data were collected from 571 Generation Z consumers engaged in social commerce in Shanghai, China. Structural equation modeling (SEM) and machine learning techniques were employed to test the proposed relationships and evaluate predictive validity. The results reveal that DTE significantly increases impulse buying behavior both directly and indirectly through PSE. Specifically, PSE serves as a significant mediator by reducing the psychological friction associated with spending, thereby encouraging impulse buying decisions. In contrast, PSC acts as a significant moderator that weakens the positive relationship between DTE and impulse buying by enhancing consumers’ perceived ability to regulate their spending behavior. These findings demonstrate that spendception operates through two opposing psychological mechanisms: spending facilitation and spending control. This study contributes to the literature by conceptualizing spendception as a distinct transaction-centered construct and by extending the SOR framework through a dual-mechanism explanation of how digital commerce environments simultaneously encourage and restrain impulsive consumption. Full article

Urban air-quality monitoring networks are often sparse, leaving coverage gaps where particulate matter (PM) concentrations cannot be directly observed. This paper extends the CityAirQ pollution tracking platform and its mobile air-quality device prototype by introducing an AI-based benchmark for two Bucharest station networks across three deployment-oriented tasks: multi-station temporal forecasting (Task A), leave-one-station-out same-day spatial estimation (Task B), and a preliminary mobile-site prediction pilot at an uncalibrated location (Task C). The benchmark compares machine-learning models, including ensemble tree methods, recurrent neural networks, and lightweight graph-inspired architectures, evaluated under a unified time-aware rolling protocol. In Task A, the proposed Advanced Stage 0–3 pipeline achieves the best overall MAE (7.12 $\mathsf{\mu }$g/m³), a 4.7% reduction relative to Random Forest (7.47 $\mathsf{\mu }$g/m³), while the Seasonal naïve (10.41 $\mathsf{\mu }$g/m³), Persistence (11.51 $\mathsf{\mu }$g/m³), neural, and graph-inspired references perform worse under recursive forecasting. In Task B, the neighbour-only Random Forest reaches a mean $R^2$ of 0.873 on the classic four-station network and a median $R^2$ of 0.734 on the ten-station city-scale extension. Task C is reported as an exploratory six-day prediction pilot, not as deployment-grade validation: no co-located EPA FRM/FEM or equivalent reference monitor was available at the mobile location ℓ. The historical-transfer Random Forest retained a sample-limited positive PM_2.5 association with the raw mobile readings ($r=0.432$, $n=6$), while a strict one-day-ahead online persistence predictor reduced PM_2.5 MAE from 40.58 to 20.00 $\mathsf{\mu }$g/m³ on the five forecastable mobile days. Ultimately, accurate PM monitoring empowers sustainable urban planning, helping to mitigate exposure risks and supporting long-term public health and environmental sustainability initiatives. Full article

Real-time monitoring of lithium-ion capacitors (LICs) is crucial for ensuring reliability and predictive maintenance in dynamic applications such as electric transportation. However, traditional electrochemical impedance spectroscopy (EIS) techniques are complex and costly for onboard diagnostics due to their reliance on external excitation signals and dedicated hardware. Therefore, this paper presents an innovative framework for online state of health (SOH) estimation that bypasses these limitations by utilizing fast Fourier transform (FFT)-based passive impedance extraction directly from operational current and voltage signals. From experimental data, the equivalent circuit model (ECM) is developed, as well as its parameters, such as ohmic resistance, charge-transfer resistance, and Warburg diffusion. These parameters are identified through the extraction of impedance points in the low frequency region through FFT and the series resistance point using ohmic measurement, then performing a periodic curve fitting to these points. These curve fittings provide extracted ECM parameters. These parameters are used with a trained model to estimate the SOH of the monitored cell and are updated online. The proposed method was experimentally validated on five LIC cells aged under various C-rates (1C, 4C, 7C) and temperatures (35 °C, 40 °C, 50 °C), showing consistent impedance evolution with capacity fade. Validation of the utilized machine learning models, such as Polynomial Regression (PR), principal components analysis (PCA), and random forest (RF) regression, achieved SOH prediction errors as low as 2.23% compared to experimental results. The developed framework is particularly suitable for applications such as flash-charged electric buses but is broadly applicable across other energy storage systems as well. This advanced method enables real-time diagnostics without hardware modification, offering significant potential for integration into existing battery management systems (BMSs). Full article

Machine Learning (ML) techniques are increasingly being adopted in particle accelerator operations to enable efficient control of complex systems. At INFN–LNL, we investigated both offline and real-time ML-driven approaches to enhance beam quality, reduce setup time, and improve reliability across different accelerator facilities. As part of this effort, we developed Adaptive Region Bayesian Optimization (ARBO), a custom Bayesian Optimization algorithm that dynamically expands its search domain when the predicted optimum approaches a boundary. Offline studies applied ARBO to the design optimization of the medium-energy beam transport line of the ANTHEM BNCT facility. Real-time online tests demonstrated the effectiveness of ARBO. At PIAVE–ALPI, the combined transmission improved from 44.2% to 52.6%, corresponding to an ALPI-only increase from approximately 69% to 82%, approaching the theoretical maximum of 93%. At the ESS normal-conducting linac, ARBO enabled the simultaneous tuning of more than 50 control elements while improving transmission and maintaining stable trajectory correction. These results indicate that adaptive optimization strategies can substantially improve accelerator performance and support future advances in ML-assisted accelerator operations. Full article

Digital platforms are reshaping urban consumption spaces and altering the trajectory of commercial gentrification. However, research on how physical and virtual factors jointly shape commercial gentrification at the city scale remains limited. Taking the main urban area of Nanjing as a case, this study integrates platform and spatial data and applies machine learning methods to identify patterns of commercial gentrification and examine the roles of physical and virtual factors across different spatial types. The results show that: (1) typical commercial gentrification spaces in Nanjing exhibit a clear core-oriented pattern, concentrated in the traditional urban center and a limited number of emerging districts; (2) virtual factors become significantly more important as commercial gentrification intensifies, with online interaction intensity emerging as the most influential factor overall, while sentiment evaluation, influencer presence and proximity to platform hotspots play stronger roles in specific spatial types; and (3) physical and virtual factors have differentiated effects, combining in different ways to produce four distinct spatial patterns of commercial gentrification. This study reveals the differentiated roles of virtual and physical factors in shaping commercial gentrification at the city scale and enriches current understanding of urban commercial restructuring in the platform era. Full article

This study aims to provide insight into consumer purchasing decisions by integrating eye-tracking data with forecasting techniques. First, the study investigates how consumption motives (hedonic vs. utilitarian) and purchasing purposes (for oneself vs. for others) influence visual attention and decision-making processes. An experimental design was conducted with 128 participants in a simulated online shopping environment, where eye-tracking data were collected based on fixation counts and durations across defined Areas of Interest (AOIs). Second, a total of 20 input features were collected, comprising fixation counts and fixation durations for 10 review-related Areas of Interest (AOIs), and these features were evaluated across the experimental scenarios, while the binary output variable represented the participant’s purchase decision. These biometric features, together with scenario information, were used to forecast purchasing decisions using six machine-learning methods, including Artificial Neural Networks, Random Forest, Support Vector Machine, K-Nearest Neighbors, Naive Bayes, and Logistic Regression. The results indicate that consumers’ visual attention aligns with their consumption motives and purchasing purposes, revealing distinct gaze patterns across different scenarios. In the forecasting phase, the accuracy of different methods for predicting purchasing decisions using review-related eye-tracking data is evaluated. Support Vector Machines achieved the highest overall accuracy, approximately 59–60% across the evaluated datasets, compared with a validation-specific majority-class baseline of 53.85%. This corresponds to a modest improvement of approximately 5.15–6.15 percentage points over the naive benchmark. Overall, the findings suggest that objectively recorded review-related eye-tracking data can be operationalized as behavioral input features in a machine-learning-based purchase-decision classification framework, highlighting the methodological value of integrating eye-tracking insights with consumer behavior forecasting. Full article

Laser-induced breakdown spectroscopy (LIBS) offers rapid, in situ, and multi-element detection, and therefore shows strong potential for quality monitoring of metal powders in additive manufacturing. However, direct LIBS analysis of flowing metal powders is often affected by particle splashing, unstable laser–particle coupling, and plasma fluctuations, which reduce signal repeatability and detection reliability. To address these issues, this study developed an integrated measurement and classification framework for identifying cross-contamination in additive-manufacturing metal powders. A stable powder particle stream was generated through vibratory feeding and particle-flow focusing, while a hollow quartz tube with a side opening was introduced to provide cylindrical spatial confinement, thereby improving the stability of laser–particle interaction and enabling in situ spectral acquisition without pellet preparation. TC4 powder was used as the base material and AlSi10Mg powder as the contaminant, and samples with contamination levels of 0, 0.5, 1, 2, and 5 wt.% were prepared. Two independent batches of single-shot LIBS spectra were collected. To reduce the influence of strong spectral fluctuations, outlier spectra were removed using full-spectrum total-intensity quantile filtering, followed by asymmetric least-squares baseline correction and standard normal variate transformation. PCA combined with multiple machine-learning models was then applied for contamination identification. The results showed that LIBS spectra at different contamination levels exhibited distinguishable distributions in principal-component space, and the spectral differences between clean and contaminated powders became more pronounced with increasing contamination level. In binary classification, several models achieved high classification accuracy at medium and high contamination levels, while PCA-SVM-RBF showed the best performance at low concentrations. In five-class cross-validation, the 5 wt.% class exhibited the clearest decision boundary, whereas confusion remained among low and adjacent contamination levels, indicating that contamination-induced spectral responses followed a more continuous transition. These results demonstrate that the proposed spatially confined particle-flow LIBS framework combined with machine-learning classification can effectively achieve rapid identification of cross-contamination in additive-manufacturing metal powders and provides a feasible technical route for online powder quality monitoring. Full article

The purpose of this study is to investigate the extent to which tourists appreciate sustainable tourism and what effect eco-friendly practices have on the decision-making process of selecting a hotel. Through the use of large-scale analysis of online reviews of hotels and the application of sentiment analysis techniques, the research investigates the impact of environmental factors (e.g., energy usage reduction, minimising waste, and promoting nature experiences) on customer perspectives and decision-making processes for lodging. This research adopts an approach that utilises machine-learning-based sentiment analysis as its source of understanding. The results of this research demonstrate that while more individuals are becoming aware of sustainable tourism, sustainability often plays a secondary role in determining whether or not to stay at a specific hotel compared to lodging attributes such as comfort, price, and quality service. Based upon these findings, this research indicates that while many tourists value sustainable tourism and make an effort to choose eco-friendly lodging establishments, the influence of sustainability on tourists’ lodging decisions is not as strong as other attributes. These results indicate important implications for hotel managers that will help them balance environmental stewardship with a competitive stance. Full article

Large-scale online reviews provide a valuable source of user feedback, yet existing methods still offer limited support for transforming massive review corpora into structured and decision-relevant requirement knowledge. Rule-based and manually intensive approaches are difficult to scale, while direct end-to-end use of large language models often faces challenges in maintaining stable requirement structures and practical large-scale deployment. To address these limitations, this study proposes a staged framework for mining user requirements from vehicle online reviews, with a particular focus on supporting early-stage requirement engineering. The framework uses large language models for requirement taxonomy construction and automatic annotation and transfers large-scale requirement categorization to a BERT classifier to balance semantic capability with deployment efficiency. A mini-batch iterative strategy is further introduced to progressively induce requirement categories from review data rather than fully predefining them in advance. In addition, sentiment weighting is incorporated to prioritize requirement categories and better reflect user pain points in subsequent analysis and decision support. Experiments on 467,962 review texts show that the proposed method outperforms several conventional machine learning and deep learning baselines on the studied dataset. Beyond quantitative evaluation, the study also examines the structural characteristics of online review-based requirement identification and explores the applicability of the framework in other review scenarios. Overall, the proposed framework provides a practical systems-oriented workflow for large-scale requirement analysis and contributes a review-based approach to early-stage requirement engineering, including requirement identification, categorization, prioritization, and interpretation. Full article

Against the backdrop of China’s vigorous promotion of rural revitalization, traditional villages have become important carriers of rural tourism; however, their tourism development potential varies significantly. Using 182 traditional villages in Shexian County, Anhui Province, as the study area, this paper integrates multi-source data, including remote sensing, socio-economic, and online data. It constructs an evaluation index system from three dimensions: resource endowment, socio-economic conditions, and natural environment. Three machine learning models, namely, Random Forest (RF), XGBoost, and LightGBM, are employed to measure tourism development potential, and the optimal model is selected through comparative analysis. On this basis, the SHAP method is introduced to interpret the influencing factors and reveal the direction and mechanisms of their effects. The results show that (1) the LightGBM model performs best and is more suitable for evaluating tourism development potential of traditional villages; (2) service facilities, land resources, and transportation conditions are the most important influencing factors, while cultural resources and online attention also play significant roles; (3) the effects of different factors exhibit obvious nonlinear characteristics with interaction effects; and (4) the spatial pattern of tourism development potential presents a structure of “core agglomeration–transitional distribution–peripheral dispersion”. From the perspective of multi-source data and explainable machine learning, this study provides a systematic analysis of tourism development potential in traditional villages and offers a scientific reference for their differentiated development and conservation. Full article

The increasing penetration of renewable energy sources in inverter-dominated microgrids introduces significant challenges for maintaining voltage and frequency stability under weak-grid and dynamically varying operating conditions. Conventional inverter control strategies, including droop control and virtual synchronous machine (VSM) methods, often exhibit limited adaptability and degraded transient performance under renewable intermittency and uncertain load variations. This paper proposes a physics-informed neural-network (PINN)-based supervisory framework for real-time grid-forming inverter control. The proposed approach embeds swing-equation dynamics, Kirchhoff-based electrical constraints, and stability-aware objectives directly into the neural-network optimization process to improve physical consistency, robustness, and operational reliability. The controller is trained offline and deployed for low-latency online inference on an NVIDIA Jetson AGX Xavier embedded platform. Simulation and hardware-in-the-loop validation results demonstrate improved transient stability, reduced frequency deviation, enhanced voltage regulation, and superior robustness compared with conventional droop, VSM, and purely data-driven neural-network controllers. The proposed framework achieved an average inference latency of approximately 0.7 ms while maintaining stable operation under renewable intermittency, load disturbances, and weak-grid conditions. The results demonstrate the potential of physics-informed machine learning for supervisory real-time control of inverter-dominated microgrids and intelligent renewable energy systems. Full article

Carrying out quality grading detection on the harvested dragon fruit is an important step in the dragon fruit industry. To reduce the high costs and damage rates caused by this process, an online spectral sensor and a weighing sensor embedded at the end effector of the dragon fruit-picking robot were designed to detect the sugar content, hardness and weight of the dragon fruits in real time during the picking process, thereby achieving the quality classification of the dragon fruits. After collecting the spectral data of dragon fruit, typical linear and nonlinear machine learning methods were used to establish prediction models for SSC-edge, SSC-center and hardness of dragon fruit. The results showed that PLSR models were selected as optimal models for prediction sugar content and hardness, and R² of test set for SSC-edge, SSC-center and hardness are 0.876, 0.826 and 0.902, respectively. Subsequently, the dragon fruits were classified based on the weighing sensor, and the SSC-center and hardness were predicted. The results showed that the established quality prediction model and the prototype could achieve the integrated operation of non-destructive quality detection and grading of dragon fruit during picking. The study provides technical support for the intelligent upgrade of fruit-harvesting equipment and the grading operations. Full article

To meet the requirements of precise temperature regulation in solar greenhouses, traditional machine learning algorithms often suffer from poor adaptability, high energy consumption, and difficulties in integrating agronomic expertise. This study developed an intelligent greenhouse temperature regulation framework based on Model Predictive Control (MPC). The core components of the framework include: (1) an expert-experience-based simulator using a Sparrow Search Algorithm-optimized Random Forest (SSA-RF) model to digitize the temperature management strategies of high-yield farmers into dynamic reference trajectories and (2) a hybrid prediction model (CNN-BiLSTM-Attention) combining Complete Ensemble Empirical Mode Decomposition with Adaptive Noise-Permutation Entropy (CEEMDAN-PE) denoising with a Convolutional Neural Network (CNN), Bidirectional Long Short-Term Memory (BiLSTM), and Attention mechanism to achieve high-precision multi-step temperature forecasting. Validation in a cucumber solar greenhouse demonstrated that the SSA-RF model achieved an R² of 0.976 on the test set, showing a significant improvement over the traditional RF model. Compared to the conventional LSTM model, the hybrid prediction model reduced the RMSE to 0.642 and 0.947 for 15 min and 30 min predictions, respectively, with a maximum R² of 0.994 and excellent generalization capabilities. Finally, these two components were theoretically integrated into an MPC-oriented decision framework. The framework describes how expert reference trajectories, multi-step predictions, actuator constraints, and control increments can be combined in a receding-horizon optimization problem. Since online actuator control data were not available, the MPC module was formulated as a theoretical decision framework rather than a fully validated closed-loop controller. This study provides a modelling basis and technical path for future real-time greenhouse temperature control. Full article

This paper addresses issues such as nonlinearity, model uncertainty, and multiple policy constraints within the dynamic evolution of new quality productive forces systems. It proposes a research framework integrating data-driven modelling with adaptive tracking control. By merging control theory with economic dynamics, a closed-loop analytical system of ‘theory-data-control’ is constructed, providing a methodologically rigorous yet operationally feasible pathway for the precise regulation of complex economic systems. First, utilising provincial panel data, a discrete-time system model integrating linear inertia, policy effects, and nonlinear compensation is established. System parameter identification is achieved through a dual machine learning approach employing partial linear regression. Subsequently, a tracking controller integrating data-driven initial identification with online parameter adaptation is designed, incorporating a projection mechanism to strictly ensure policy variables remain within feasible adjustment ranges. Based on Lyapunov stability theory, we demonstrate that the tracking error of the closed-loop system exhibits ultimate convergence with boundedness. Simulation experiments confirm that the proposed method significantly enhances the system’s tracking performance towards the target trajectory, reducing the mean absolute error by approximately 30.8% while producing smoother control signals. Comparative studies indicate that the parameter adaptation mechanism and nonlinear compensation module play crucial roles in improving control effectiveness. This research not only expands the theoretical toolkit for analysing the dynamics of new quality productive forces but also provides an interdisciplinary methodological reference for the closed-loop management of complex socioeconomic systems under data-driven conditions. Full article