As bandwidth-intensive applications proliferate and the usage of wireless devices surges, fifth-generation (5G) and beyond (B5G) networks are challenged to enhance coverage, reduce latency, and improve efficiency. The application of machine learning (ML) models for received signal strength (RSS) estimation is a powerful tool. This study evaluates various ML models—categorical boosting (CatBoost), extreme randomized trees (ETs), light gradient boosting machine (LGBM), and extreme gradient boosting (XGBoost)—for effective estimation of RSS. Additionally, we apply explainable artificial intelligence (XAI) methodologies, especially the Shapley additive explanation (SHAP) framework. Our investigation reveals the sophisticated mechanisms within these models, notably highlighting the exceptional accuracy of the ET model. We further introduce SHAPRP, in which SHAP attributions reduce the input space and sparse regression selects a compact subset of the ET ensemble. The results are obtained from a single-operator rural/semi-rural campaign and constitute a case study, where the trained estimator is deployment-specific and is not a pre-trained model applicable to arbitrary 5G/B5G scenarios, so what transfers is SHAPRP itself.
Background: Immersive virtual reality (VR) may support rehabilitation and patient engagement; however, little is known about how frontline healthcare professionals perceive its clinical relevance and feasibility in post-acute community care settings. This study explored healthcare professionals’ perceptions of the potential clinical uses, usability, and implementation requirements of patient-facing immersive VR in a community hospital providing post-acute care in Singapore. Methods: Using purposive sampling, nineteen healthcare professionals from a subacute hospital in Singapore participated in individual semi-structured interviews. Participants discussed their expectations of VR, experienced approximately 10–15 min of a reminiscence-oriented virtual tour of a local (now defunct) village, using an Oculus Quest head-mounted display, and subsequently reflected on its usability and potential applications. The Unified Theory of Acceptance and Use of Technology 2 informed the interview guide and was used as a sensitising framework. Interviews were transcribed verbatim and analysed using hybrid deductive–inductive framework analysis. Results: Four themes were identified: (1) clinical value was conditional on therapeutic relevance; (2) anticipated patient acceptability depended on person–content fit and social context; (3) simple navigation did not remove physical and sensory barriers; and (4) clinical integration required a supporting service model. Conclusions: Healthcare professionals viewed immersive VR as potentially useful but not yet ready for routine clinical implementation. Adoption in post-acute care should be guided by therapeutic purpose, accessibility, and integration into existing workflows rather than technological novelty alone. Future research and development should prioritise co-designed therapeutic content, patient selection, accessibility, workflow integration, and implementation support.
Detecting traffic signs in real-world roadway scenes remains a demanding task due to extensive category diversity, the prevalence of diminutive targets, and interference from cluttered surroundings. To overcome these obstacles, we present YOLO-PPA, a YOLOv11n-based detector strengthened through multi-path feature aggregation and attention-enhanced representation learning. First, a Parallelized Patch-Aware Attention (PPA) mechanism is embedded in place of the standard C3K2 block, simultaneously capturing fine-grained local textures and broad contextual semantics while adaptively amplifying informative spatial regions critical for small objects. Second, a high-resolution P2 detection head is appended to the feature pyramid, recovering fine spatial cues that would otherwise be attenuated across successive downsampling stages, and this design is particularly beneficial for recognizing signage occupying only a handful of pixels. Third, the Normalized Gaussian Wasserstein Distance (NWD) replaces the conventional CIoU metric as the regression loss, offering a smoother optimization landscape for tiny instances where even single-pixel displacements can destabilize standard IoU-based objectives. Evaluated on the TT100K benchmark, YOLO-PPA surpasses the YOLOv11n baseline by 2.1% in precision, 3.7% in recall, 4.3% in mAP@50, and 3.0% in mAP@50:95, confirming its effectiveness for small-scale traffic sign recognition in complex driving environments.
The recovery of zinc from mixed steelmaking and blast furnace sludge was investigated through a direct comparison of the hydrometallurgical acetic acid leaching process and pyrometallurgical processing using coke dust as a reductive agent, with particular emphasis on the structure and functional properties of the resulting ZnO products. The mixed sludge contained 9.71 wt.% ZnO, with zinc occurring predominantly in the form of stable ferritic phases, mainly franklinite ((ZnFeII)Fe2O4). Hydrometallurgical treatment using 1 mol·dm−3 acetic acid resulted in only a limited relative decrease in Zn content (16.8%) based on solid-phase concentrations, as mainly readily soluble zinc phases were dissolved, while ferrite-bound zinc remained largely unaffected. In contrast, pyrometallurgical treatment of the sludge–coke dust mixture at 1200 °C enabled highly effective zinc volatilization, reducing the residual Zn content below 0.05 wt.% and resulting in a relative decrease in Zn content of 99.5% based on solid-phase concentrations. Characterization by XRD, FTIR, SEM, and EDS revealed substantial differences between the products obtained by the two processing routes. The pyrometallurgically prepared ZnO-rich product exhibited higher crystallinity, well-developed rod-like morphology, and substantially lower Fe and Pb contamination than the hydrometallurgically prepared material. In contrast, the hydrometallurgical product showed lower crystallinity and elevated Fe and Pb contents and therefore represented a highly contaminated ZnO-rich oxide mixture. Photocatalytic tests using Rhodamine B showed measurable but low activity of the pyrometallurgical product, with approximately 18% degradation after 120 min of UV irradiation, whereas the hydrometallurgical product was practically inactive. Overall, carbothermic treatment provided substantially more effective Zn removal than acetic acid leaching, although the recovered ZnO-rich product exhibited only limited photocatalytic activity.
In order to improve maximum power point tracking (MPPT) and energy extraction in grid-connected photovoltaic (PV) systems under various climatic conditions, this research proposes a Secretary Bird Optimization-tuned Super-Twisting Sliding Mode Controller (SBOA–STSMC). The efficacy of traditional MPPT and adaptive control techniques is frequently compromised by nonlinear dynamics, abrupt changes in irradiance, and partial shading. In order to overcome these restrictions, the suggested method uses the Secretary Bird Optimization Algorithm (SBOA) to optimize STSMC parameters, resulting in improved disturbance rejection and transient response. Five increasingly difficult simulation scenarios are used to evaluate the controller. A single-array grid-connected system under stepwise irradiance fluctuations, combined irradiance–temperature disturbances, severe atmospheric dynamics, and low-irradiance operation are examined in Scenarios 1–4. The performance of adaptive controllers tuned using the Harmony Search Algorithm (HSA) and Invasive Weed Optimization (IWO) is compared with the traditional Incremental Conductance approach. In the fifth scenario, which deals with dynamic partial shading in a dual-array arrangement, the suggested approach is contrasted with HSA-based and IWO-based adaptive controllers and the traditional Perturb and Observe (P&O) technique. Furthermore, a sensitivity analysis is carried out for ±50% parameter modifications, demonstrating a small change in the total injected energy. An additional severe-disturbance test under rapid irradiance variations is performed, together with a ±50% sensitivity analysis of the grid-side choke inductance under the same severe profile. Statistical repeatability is further evaluated through 30 independent runs of the SBOA. A separate statistical comparison based on 30 independent runs of SBOA, TLBO, and PSO is also performed using the Wilcoxon rank-sum test, supporting the superior and consistent performance of SBOA. In addition, real-time validation is conducted using a Speedgoat real-time platform to demonstrate the practical implementation capability of the proposed controller. The results confirm improved dynamic response, reduced oscillations, enhanced robustness, and increased energy injected into the grid across all considered operating conditions.
We present a comprehensive empirical study of attention mechanisms for eye-based driver drowsiness detection, evaluating 13 model variants across accuracy, calibration, cross-dataset generalization, and FPGA edge deployment. We introduce the Guided Dual-Attention Unit (GDAU), which combines position-aware spatial attention with SE channel attention. The data pipeline first splits the full imbalanced dataset (103,803 images, 5.9:1 ratio) into stratified train/validation/test subsets; then, it applies undersampling only to the training set. On the naturally imbalanced test set, no attention mechanism significantly outperforms the others on an identical backbone: Channel attention achieves the highest raw accuracy (83.86%), while CBAM-L achieves the highest balanced accuracy (86.77%) and ROC AUC (0.927). GDAN achieves 82.83% accuracy (85.99% balanced) with only 2.19 M parameters—half of the baseline’s 4.29 M. Component ablation confirms spatial–channel complementarity (+2.37% balanced accuracy over baseline). No single model dominates all calibration metrics. Cross-dataset transfer fails for all architectures (48–57%, near random chance). On the physical Xilinx Kria KV260, DPU-accelerated inference achieves 0.481–1.116 ms (896–2077 FPS), confirming real-time edge deployment feasibility.
This study presents a data-driven framework for determining the optimal gear tooth surface modification (crowning) to improve tolerance to angular misalignment (in-plane and out-of-plane). A nonlinear tooth contact analysis (TCA) model was employed to accurately predict the contact path evolution of meshing gears under different combinations of tooth modification amounts and misalignment angles. An accurate dataset consisting of 530 simulated helical gear meshing configurations was generated. Based on these simulation results, a Gaussian Process Regression (Kriging) surrogate model was developed to establish the relationship between tooth modification, misalignment parameters, and contact behavior. The validated surrogate model enables rapid prediction of gear contact characteristics and interpolation within the design space, thereby supporting efficient surrogate-assisted design exploration without requiring repeated computationally intensive TCA simulations. The proposed framework identifies the minimum modification required to maintain acceptable contact conditions, and provides an efficient tool for improving misalignment tolerance and supporting robust gear design.
Efficient maximum power extraction in variable-speed wind energy conversion systems (WECSs) remains challenging because of nonlinear turbine dynamics, continuously varying wind conditions, measurement disturbances, and mechanical-parameter uncertainties. This study presents a robust nonlinear integral backstepping control (BC) strategy for generator-speed regulation within a Tip-Speed Ratio (TSR)-based Maximum Power Point Tracking (MPPT) framework. The proposed controller combines nonlinear backstepping stabilization with integral compensation to improve reference tracking and reduce persistent tracking errors. The turbine-generator mechanical inertia is explicitly incorporated into the control formulation, providing a physically consistent representation of the mechanical dynamics and enabling systematic evaluation of parameter uncertainty. A comprehensive comparative assessment is conducted in MATLAB/Simulink using four control strategies: proportional-integral (PI), integral-proportional (IP), sliding-mode control (SMC), and the proposed integral BC. The controllers are evaluated under five complementary scenarios: variable wind speed, measurement noise, abrupt stepwise wind-speed variations, ±20% mechanical-inertia uncertainty, and a 10-ms rotor-speed measurement delay. Performance is assessed using the Integral of Squared Error (ISE), Integral of Absolute Error (IAE), and Integral of Time-weighted Absolute Error (ITAE), together with statistical measures across the five scenarios. Under the baseline variable-wind condition, BC achieves ISE = 24.4164, IAE = 1.539, and ITAE = 0.716, outperforming PI, IP, and SMC in all three indices. Under abrupt stepwise wind-speed variations, BC further achieves ISE = 0.00110, IAE = 0.0056, and ITAE = 0.0529, demonstrating rapid transient error suppression. The proposed controller remains stable under ±20% mechanical-inertia variations and a 10-ms measurement delay. Across the five scenarios, BC achieves the lowest mean ISE, IAE, and ITAE values of 19.353, 1.231, and 2.642, respectively, as well as the lowest standard deviations for ISE and IAE. SMC exhibits particularly consistent performance under measurement noise and the lowest standard deviation for ITAE. Overall, the results demonstrate that the proposed integral BC provides the most favorable balance of tracking accuracy, transient performance, and robustness among the investigated strategies. The improved rotor-speed regulation supports operation near the optimal TSR and effective aerodynamic power extraction. The findings highlight the potential of the proposed approach for robust MPPT control of variable-speed WECSs.
Energy systems are crucial to residential life and industrial production. During practical operation, these systems may experience various anomalies that disrupt the stability of system operation. Recent years have witnessed remarkable progress in power system anomaly detection. However, existing methods still suffer from two limitations. First, detection algorithms neglect privacy protection, although privacy security is also a critical issue in energy systems. Second, existing studies have difficulty characterizing latent dependencies and topology changes, which limits detection performance. To bridge these gaps, we present a power system anomaly detection method that integrates physics-informed sparse graph temporal modeling with homomorphic encryption, enabling anomalous-event identification and anomalous-bus localization under privacy-preserving conditions. Specifically, we construct a sparse graph using the power-grid topology and normal measurement residuals. We then obtain system-state predictions through polynomial graph temporal prediction and physics-guided affine correction and use anomaly scores to diagnose anomalous conditions. Furthermore, we employ homomorphic encryption to perform ciphertext computation for the affine prediction model without exposing historical measurement data, thereby enabling privacy-preserving remote anomaly detection. We conduct experiments on IEEE bus benchmarks to verify the effectiveness of the proposed method under multiple anomaly scenarios.
The integration of unmanned aerial vehicles (UAVs) as aerial base stations has emerged as a key enabler for next-generation wireless networks, particularly in disaster recovery, temporary events, and infrastructure-deficient regions. However, multi-UAV deployments introduce severe co-channel interference due to spectrum reuse and overlapping coverage areas, while existing spectrum allocation methods either rely on centralized optimization with limited scalability or on reinforcement learning frameworks that lack spatial awareness of interference sources. To address these challenges, this paper proposes a Hybrid DeepMUSIC-assisted Cooperative Multi-Agent Deep Reinforcement Learning (MADRL) framework for intelligent spectrum allocation and interference management in multi-UAV 6G networks. The proposed framework integrates a hybrid interference localization module, which fuses the classical MUltiple SIgnal Classification (MUSIC) algorithm with a deep neural network to accurately estimate the direction of arrival (DoA) of interference sources, into a DeepMUSIC-enhanced state representation used by cooperative Deep Q-Network (DQN) agents trained under a Centralized Training and Decentralized Execution (CTDE) paradigm, enabling coordinated yet fully distributed spectrum allocation decisions. Extensive simulations demonstrate that the proposed Hybrid DeepMUSIC module reduces the mean DoA estimation error to approximately 0.105°, more than an order of magnitude better than classical MUSIC and standalone DeepMUSIC estimators. Compared with seven baseline algorithms spanning heuristic, optimization-based, single-agent, and cooperative multi-agent reinforcement learning approaches, the proposed framework achieves the highest network throughput, SINR, spectrum efficiency, and energy efficiency, together with the fastest and most stable training convergence, reaching a stable cooperative reward of 76.246 within approximately 371 training epochs. The framework further maintains near-linear computational scaling with the number of UAV agents, confirming its suitability for real-time deployment in dense, AI-native multi-UAV 6G wireless communication systems.
Overlapping cells in plant suspension-culture microscopy pose a particular challenge, for instance, segmentation because a single pixel may belong to more than one cell. Most standard instance-segmentation methods are not designed for this setting and tend to treat overlapping objects as mutually exclusive regions. We instead represent each cell as an independent full-cell instance and introduce MC-SlotNet, an architecture that separates competitive object-slot feature assignment from mask decoding. This allows multiple predicted masks to occupy the same image region. We further introduce a mask-level multiplicity-consistency loss that encourages the predicted number of masks covering a pixel to agree with the underlying cell occupancy. We evaluate MC-SlotNet on a newly annotated dataset of 53 Siraitia grosvenorii suspension-culture micrographs containing 4131 full-cell instances acquired at 4×–40× magnification. Using grouped five-fold cross-validation and an overlap-preserving evaluation protocol, we compare the method with Mask R-CNN, SOLOv2, and Mask2Former. MC-SlotNet achieves the best performance on AP50 (0.800), mAP50:95 (0.565), F150 (0.842), all-ground-truth Dice (0.761), AJI+ (0.754), overlap-region Dice (0.705), and overlap-instance recall (0.828). Its AP75 (0.649) is comparable to Mask2Former’s (0.651). MC-SlotNet also has the lowest inference time among the evaluated methods, at 1.113 s/image. These results indicate that decoding full-cell masks independently, rather than enforcing an exclusive partition of image pixels, is well-suited to instance segmentation in plant suspension-culture microscopy images with substantial cell overlap.
Rapid and non-destructive assessment of sweet potato quality is important for postharvest management, processing suitability evaluation, and market quality control. In this study, a 12-channel visible/near-infrared (Vis/NIR) spectral sensing system was applied to predict multiple physicochemical quality attributes of postharvest sweet potatoes. Sixty independent sweet potato storage roots were measured at three representative positions, producing 180 position-specific observations; measurements from the same root were retained within the same validation group. The measured attributes included dry matter content (DMC), starch content (SC), soluble solids content (SSC), and the CIE 1976 L*a*b* (CIELAB) color coordinates L*, a*, and b*. Four spectral treatment conditions, including original spectra, normalization, standardization, and first-derivative transformation, were combined with partial least squares regression (PLSR), multiple linear regression (MLR), extreme gradient boosting (XGBoost), and random forest (RF), generating 16 prediction strategies for each quality attribute. Root-grouped five-fold cross-validation showed that the optimal models achieved coefficients of determination for cross-validation (R2CV) ranging from 0.9083 to 0.9190 and residual predictive deviation (RPD) values ranging from 3.3112 to 3.5230. Repeated grouped cross-validation produced mean R2CV values of 0.9113–0.9176, and root-block Y-scrambling yielded empirical p values of 0.005 for all six attributes. PLSR provided the highest cross-validated performance for all six quality attributes, although MLR showed comparable performance for several targets. These results provide preliminary evidence that discrete Vis/NIR spectral sensing can support simultaneous non-destructive estimation of multiple sweet potato quality attributes. External multi-batch and multi-cultivar validation is required before the models can be considered robust for practical deployment.
This study evaluated the effects of uniform and symmetric step-gradient infill architectures on the density, mechanical properties, Shore D hardness, and dry-sliding coefficient of friction of FFF-printed thermoplastic polyurethane (TPU) 95A. Uniform triangular infills at 50%, 70%, and 90% were compared with a surface-dense architecture (GI-1: 90–70–50–70–90%) and a core-dense architecture (GI-2: 50–70–90–70–50%). The experimental density of GI-2 (0.988 g/cm3) did not differ significantly from that of the uniform 70% configuration (0.990 g/cm3). GI-2 nevertheless exhibited significantly higher tensile strength (20.3 vs. 18.4 MPa) and a higher work of deformation to failure (48.3 vs. 32.3 MJ/m3). GI-1 had a lower experimental density than the uniform 90% configuration yet higher tensile strength and work of deformation to failure; the two configurations were not density-matched. Both gradient architectures exhibited lower mean compressive stresses at 20% strain than the uniform 70% and 90% specimens. GI-1 displayed a Shore D hardness comparable to the uniform 90% configuration and the lowest mean coefficient of friction (0.50 ± 0.01). Overall, step-gradient infill can improve specific tensile properties while allowing compressive compliance and the contact response of the outer shell to be tailored separately. However, the effects of gradient order and material content could not be fully separated because GI-1 and GI-2 differed in nominal mean infill density.
AI-generated and locally manipulated images can support impersonation, forged evidence, identity-document abuse, and other forms of digital fraud, making reliable content-authenticity analysis increasingly important. This paper presents STeREx-Net, a three-class forensic framework for distinguishing real, fully synthetic, and locally tampered images using frozen diffusion-derived residual evidence, spatially aligned RGB features, multi-task prediction heads, and reviewable visual evidence. On the official balanced 60,000-image SID-Set test, the original model achieved 96.24% accuracy, 96.26% macro F1, and a multiclass Matthews correlation coefficient of 0.944. Separate matched three-seed ablations showed that diffusion-residual evidence is materially useful relative to RGB-only input; however, residual-only and simple-fusion controls outperformed the proposed fusion on the clean SID-Set, so fusion superiority is not claimed. Frozen robustness testing further revealed strong condition dependence: SID-Set macro F1 decreased from 0.9655 on clean images to 0.7987 under JPEG Q75 and 0.6330 under JPEG Q50, while generator-stratified AIS-4SD results also varied substantially. Zero-shot transfer to FantasyID failed to detect tampered samples, whereas leakage-safe restricted adaptation partially recovered tampered recall to 0.3447 and reduced the expected calibration error from 0.7815 to 0.2077, at the cost of lower real-image recall. A validation-selected localization intervention increased Dice from 0.2817 to 0.3413 but remained precision-biased and non-uniform across manipulation sizes. Quantitative explanation analysis supported in-domain decision faithfulness and benign-transformation stability, but these properties did not transfer consistently to external data. STeREx-Net should therefore be viewed as a human-supervised forensic research framework with explicitly characterized robustness, localization, and generalization boundaries rather than as a universally robust detector.
The main scope of this research was to complete and validate the analysis of stator winding topologies of six-phase AC machines using the winding quality factor by determining fault tolerance and validating it through experimental tests. This paper proposes a unified and practical methodology for evaluating the performance of stator windings in six-phase induction machines, with emphasis on magnetic field quality and fault-tolerant operation. The approach combines analytical modeling of the magnetomotive force (MMF) with its graphical representation using the MMF polygon, enabling an efficient assessment of harmonic content through a global indicator, referred to as the winding quality factor. Several representative winding topologies are analyzed within a common framework, including single-layer and double-layer configurations with full-pitch and short-pitch coils, suitable for generating homologous series of six-phase machines. The study considers both normal operating conditions and post-fault regimes, particularly operation with a single three-phase set. The results reveal the strong influence of winding topology on harmonic distortion and overall machine performance, highlighting the trade-offs between magnetic field quality and fault tolerance. It is shown that appropriate winding design can reduce spatial harmonics and improve robustness under degraded operating conditions. The theoretical findings are validated through experimental investigations, demonstrating good agreement between analytical predictions and measured data. A parallel analysis was performed between the theoretical findings and experimental data, and the results conform to the authors’ expectations.
Repeated dyadic interactions are characterized not only by average multimodal signal levels but also by how cross-modal consistency evolves over time. This study investigated whether the joint temporal organization of within-person face–body cross-modal consistency and probabilistic cross-modal affective agreement, quantified by the Consistency Index for Affective Synchrony (CIAS) and the Probabilistic Multimodal Consistency Index (PMCI), yielded reproducible session-level dynamic representations associated with repeated dyadic interaction. The primary analysis included 24 improvised and 17 naturalistic sessions, with 12 dyads in each condition. Time-varying signals from both partners were summarized through dynamic-state occupancy, dwell structure, transition characteristics, and temporal variability and evaluated using relational permutation analysis with shared-participant and technical controls. In naturalistic interaction, repeated sessions of the same dyad were significantly more similar (β = −2.0180, FDR q = 0.0114), with significant dyad-specificity beyond shared-participant similarity (Δβ = −2.4670, q = 0.0033). Representation ablations showed that PMCI provided the dominant state-separation structure, whereas CIAS contributed modest and condition-dependent complementary information. Most notably, frozen participant-disjoint evaluation on 73 naturalistic sessions from six dyads and 11 previously unseen participants retained significant dyad-associated structure and achieved session-weighted nearest-dyad accuracy of 0.8356 and macro-dyad accuracy of 0.8512. Additional robustness analyses showed that the principal pattern persisted across state-count specifications, temporal-window settings, partner-order reversal, and explicit technical-quality adjustment. Overall, the findings support the existence of reproducible session-level multimodal dynamic structure associated with repeated dyadic interaction and its transfer to previously unseen participants, while not implying direct interpersonal synchrony or psychologically defined interaction states.
Concentrated solar power systems can provide dispatchable renewable energy, but their application in distributed cogeneration is constrained by high costs and thermal losses associated with indirect heat transfer. This study proposes a direct vapour generation cascade organic Rankine cycle (DVG-CORC) for combined heat and power production. A biphenyl–diphenyl oxide (BDO) mixture is used as both the solar-collection fluid and the high-temperature cycle working fluid, while thermal storage and four operating modes are incorporated to accommodate variations in solar irradiance and enable continuous operation. Thermodynamic and economic models are developed to evaluate system performance under different evaporation and condensation temperatures. At an evaporation temperature of 400 °C, the maximum thermal efficiencies are 37.67%, 35.38%, and 33.11% at condensation temperatures of 60 °C, 80 °C, and 100 °C, respectively. At a condensation temperature of 60 °C, the cogeneration system generates an estimated annual revenue of USD 929,637, which is USD 284,269 higher than that of the power-generation-only configuration operating at a condensation temperature of 30 °C. These results demonstrate that direct vapour generation, cascade energy utilization, and heat recovery can improve the thermodynamic and economic performance of distributed solar cogeneration systems.
The application of artificial intelligence (AI) and the Internet of Things (IoT) is transforming smart hotel services by simultaneously creating technological benefits and privacy-related concerns. Although previous studies have extensively examined the effects of AI and IoT on tourist experiences, they have predominantly adopted an individual perspective, with limited attention to potential interdependence among co-present guests. This study examines how technological benefits (AI usefulness, IoT convenience, and personalization) and technological risk (perceived privacy risk) are associated with tourists’ satisfaction and electronic word-of-mouth (eWOM) intention, while also investigating whether these outcomes exhibit dependence across social, spatial, and temporal structures of guest co-presence. The study draws on survey data collected from tourists staying in AI-and IoT-enabled hotels in Hungary, Croatia, and Serbia. The findings show that AI usefulness, IoT convenience, and personalization are positively associated with satisfaction and eWOM intention, whereas perceived privacy risk is negatively associated with both outcomes. Furthermore, technological benefit constructs exhibit significant positive indirect associations across guest co-presence structures, whereas privacy risk exhibits less consistently statistically significant indirect associations, particularly for eWOM intention. These findings indicate the coexistence of positive technology evaluations and privacy concerns and reveal different patterns of co-presence-associated interdependence rather than demonstrating that technological benefits statistically dominate privacy risks. These findings contribute to smart hospitality research by extending the benefit–risk perspective beyond exclusively individual-level evaluations and highlighting the importance of considering conditional interdependence among co-present guests when evaluating AI- and IoT-enabled hotel services.
Impulsivity is a common trait and is understood as a symptom of various disorders such as Attention-Deficit/Hyperactivity Disorder (ADHD). We previously proposed ImpulsivityBank protocol, which is a standardized discourse protocol for retrieving speech samples that enables the identification of the speech features related to the impulsivity trait in children and adolescents. ImpulsivityBank protocol presents three elicitation methods (recall task, storyboard, picture description) and quantifies general language abilities using a battery of linguistic assessments. In this paper, we analyze the current data from the Impulsivity corpus, which is a corpus that consists of speech samples collected using our protocol. We performed an automated linguistic-feature analysis of the Impulsivity corpus to examine speech features related to the impulsivity trait in children and adolescents. We present the results of both the classification and prediction systems considering diverse experimental scenarios. Our results indicate that the speech features from the storyboard consistently yielded the best-performing classification and prediction systems among the evaluated elicitation methods. We conclude that ImpulsivityBank protocol facilitates the collection of speech samples from which a range of linguistic features can be extracted and explored in relation to the impulsivity trait in children and adolescents. The consistency observed across the classification and prediction models suggests that multiple speech features jointly contributed to the fitted models’ outputs. Our main contribution lies in speech analysis, particularly in the extraction and study of speech features that may be associated with impulsivity.
Existing wind power optimization control strategies often lack a qualitative analysis of the relationship between wind power energy and system frequency, which may lead to insufficient or excessive frequency support, thereby reducing the effectiveness of wind power frequency support or triggering a secondary frequency drop. To address this issue, a receiving-end system frequency optimization control strategy based on the available rotor kinetic energy of sending-end wind farms is proposed. First, the mathematical expression of the approximately first-order response in the initial stage of optimized frequency dynamics is clarified. The quantitative relationship between the available rotor kinetic energy of wind farms and the frequency support level is derived, and a target frequency design method is developed by combining a conservative evaluation of effective frequency regulation energy. Second, according to the deviation between the target frequency and the measured frequency, the total frequency regulation demand calculation, the approximate calculation of synchronous generator mechanical power variation, and the wind farms’ frequency regulation command calculation are dynamically executed within each control step. In this way, the outputs of wind farms and synchronous generators are coordinated to regulate the frequency close to the target value. Finally, a simulation model is built in MATLAB/Simulink to verify the effectiveness of the proposed frequency control target design method and control strategy under different operating conditions, as well as their robustness against parameter acquisition errors, communication delays, and power disturbance estimation errors.
