Search Results (1,223)

Traffic flow prediction is an important and fundamental task for the operation of Intelligent Transportation Systems. In recent years, most studies on traffic prediction have focused on two-dimensional network traffic flow prediction, while there is still no clear consensus on the study of one-dimensional highway traffic flow prediction, for instance, regarding which model is the most appropriate. To address this gap, we conducted a systematic comparative evaluation of 27 models across five classes, including Statistical models, Machine Learning, Artificial Neural Networks, Deep Neural Networks, and Graph Neural Networks, based on five representative highway traffic datasets. To ensure fairness, evaluations were performed on raw data without signal decomposition or auxiliary modules. Surprisingly, the experimental results reveal that complex deep learning models do not demonstrate advantages in terms of conventional metrics. Instead, simple models, particularly Historical Averaging and tree-based Machine Learning models, exhibit superior performance in most scenarios. And then, we study the underlying reasons for this phenomenon from various perspectives, including the complexity of prediction tasks, the tabular data characteristics, the spectral bias of Neural Networks, and theoretical error bounds. Furthermore, we also analyze why these findings were overlooked in the previous literature, attributing the oversight to the predominant focus on signal decomposition preprocessing, inconsistent prediction settings, and the lack of comprehensive benchmarking. Supported by rich data and extensive information, this work offers valuable references and practical implications for researchers in highway traffic flow prediction. It further advocates that in the era of pursuing sophisticated models, scenario-specific analysis and appropriate simple models still deserve more attention. Full article

This study aimed to evaluate the within-system agreement and interchangeability of real-time and post-processed external load metrics in elite football. Data were collected from 50 official Serie A matches using Dynamix (K-Sport World S.R.L., Pesaro, Italy), the platform for acquiring and standardizing tracking inputs. SmartLive, a real-time monitoring module embedded within Dynamix, was compared with post-processed data from the league-approved optical tracking provider (Hawk-Eye Innovations Limited, Basingstoke, UK) in Serie A. The external load metrics analyzed included total distance covered; distances at speeds exceeding 15, 20, and 25 km·h⁻¹; distances within the 15–20 km·h⁻¹ and 20–25 km·h⁻¹ ranges; distance covered during accelerations > 2 m·s⁻² and decelerations < −2 m·s⁻²; and peak speed. Intraclass correlation coefficients (ICCs) demonstrated excellent agreement across all metrics, with values ranging from 0.929 to 0.999. Bland–Altman analysis revealed small mean differences between systems, indicating strong agreement. Overall, the findings confirm that both real-time and post-processed data are in close agreement across a wide range of performance metrics. Minor discrepancies were observed in intermediate speed zones and acceleration/deceleration events. This study provides the first validation of SmartLive’s within-system agreement with post-processed data, supporting its use alongside post-processed data in elite football environments. Full article

We study binary hypothesis testing for i.i.d. observations under a multiplicative context weight. For the optimal weighted total loss, defined as the sum of weighted type-I and type-II losses, we prove the logarithmic asymptotic $L_n^{*}=exp\{-n{D}_C^{\mathrm{w}}(\mathbb{P},\mathbb{Q})+o\left(n\right)\},n\to \infty$, where $D_C^{\mathrm{w}}$ is the weighted Chernoff information. The single-letter form of the exponent relies on a structural assumption that the weight factorises across observations, $\phi \left(x_1^n\right)={\displaystyle \prod _{i=1}^n}\phi \left(x_i\right)$; this restriction is essential for the single-letter representation and should be distinguished from the weaker qualitative description “multiplicative context weight”. The proof embeds the weighted geometric mixtures $\phi p^{\alpha }{q}^{1-\alpha }$ into a likelihood-ratio exponential family and identifies the rate through its log-normaliser. We also derive concentration bounds for the tilted weighted log-likelihood, obtain closed forms for Gaussian, Poisson, and exponential models, and extend the exponent characterisation to finitely many hypotheses. Full article

Globba bicolor Gagnep., an ornamental ginger of cultural importance in Thailand’s “Tak Bat Dok Mai” festival, faces conservation challenges due to climate change and slow natural propagation. Limited understanding of its cultivation and chemical composition further constrains sustainable utilization. This study provides the first integrated investigation of micropropagation using rhizome-derived explants under various combinations of exogenous hormones, acclimatization strategies, and comparative phytochemical profiling between wild and in vitro-propagated plants. An optimized clonal regeneration system was established from plantlets, with Murashige and Skoog (MS) medium containing 2.0 mg/L 6-benzylaminopurine (BA) and 0.5 mg/L 1-naphthaleneacetic acid (NAA), yielding the highest multiplication (9.10 shoots/explant and 12.40 roots/explant) after eight weeks of cultivation. During acclimatization, sand substrate proved superior, facilitating a 90% survival rate and enhanced physiological vigor. Comparative analysis revealed that while wild plants possessed significantly higher total phenolic (TPC) and total flavonoid (TFC) contents and antioxidant activities (DPPH, ABTS, and FRAP) than their in vitro counterparts, both sources maintained a rich diversity of chemical constituents. HPLC analysis identified cinnamic acid, rutin, and quercetin as major metabolites, while GC–MS detected 90 volatile compounds, with β-caryophyllene and β-pinene as predominant constituents. Notably, rhizomes of wild plants exhibited particularly high-value detections. To provide a rapid and non-destructive approach for linking chemical composition with antioxidant activity, FTIR-based chemometric models were applied, demonstrating high predictive accuracy (R²–cv = 0.9712–0.9862). These results provide a scientific foundation for the conservation and sustainable commercial utilization of G. bicolor as a potential source of bioactive natural products. Full article

Background: Melanoma is one of the most aggressive forms of skin cancer, making early and accurate diagnosis essential for improving patient outcomes. Methods: In this work, we propose an Evolutionary Gabor-based Melanoma Descriptor (Evo-GMD), a lightweight and interpretable approach designed under the principles of Frugal AI. The method integrates multi-scale Gabor filtering with Differential Evolution to automatically learn discriminative texture patterns using a reduced set of parameters. The proposed approach was evaluated on the PH2 dataset, achieving competitive performance (accuracy above 95%) while maintaining low computational complexity and full interpretability. To further assess its robustness, complementary experiments were conducted on the ISIC 2017 dataset, which presents higher variability, class imbalance, and heterogeneous lesion characteristics. Results: The results reveal that multiple methods—including handcrafted descriptors, convolutional neural networks, and transfer learning models—exhibit significant performance degradation or converge to trivial solutions under these conditions. This behavior highlights that increasing model complexity does not necessarily improve classification performance when data constraints are present. Conclusions: Overall, the findings demonstrate that the proposed method provides a robust and efficient alternative for melanoma classification in low-resource scenarios, where data availability, computational capacity, and interpretability are critical factors. Full article

Accurate extreme rainfall representation is critical for resilient hydrological design and sustainable water management in tropical regions. This study evaluates the GPM IMERG product across three diverse watersheds in East Java (Welang, Kedak, and Grindulu) using Extreme Value Theory (EVT). By employing Generalized Extreme Value (GEV) and Peaks Over Threshold (POT) methods, the research assesses the reliability of satellite estimates in characterizing the extreme events that safeguard community security and infrastructure longevity. Results indicate that while GPM IMERG excels at monthly scales, it lacks the daily precision required for effective flash flood mitigation, particularly in small basins. Crucially, GEV analysis reveals a structural mismatch: ground observations exhibit heavy-tailed (Fréchet) distributions, while GPM IMERG follows bounded (Weibull) distributions. Consequently, the satellite product underestimates high-magnitude events at long return periods, the exact events that define the design limits of adaptive hydraulic structures. Complementary POT analysis identifies scale-dependent biases across catchments. These findings suggest that while GPM IMERG is robust for regional monitoring, it requires distribution-specific bias correction to support disaster-resilient engineering. Addressing these gaps is essential for achieving climate-responsive sustainable development in data-scarce regions. Full article

In response to the increasing operational complexity of inland waterway systems, this study develops a multi-objective optimization framework for ship lock scheduling under energy-consumption and resource constraints. The model evaluates five operational dimensions, namely average waiting time, lock utilization, total energy consumption, arrival rescheduling rate, and berth-overcapacity penalty. Based on historical lockage records from the Da Teng Gorge Ship Lock Hub, four representative multi-objective algorithms—NSGA-II, NSGA-III, MOEA/D, and SPEA-II—are comparatively examined. The revised analysis emphasizes trade-off performance rather than unsupported absolute dominance claims: NSGA-III shows the most balanced overall behavior on the preserved empirical instance, MOEA/D remains competitive in time-sensitive scenarios, and SPEA-II performs well in some overcapacity-control settings. To improve methodological transparency, the paper clarifies the physical meaning and source of major parameters, distinguishes measured quantities from scenario settings, and reports carbon impact as a derived indicator linked to energy consumption. These revisions provide a more transparent and practically interpretable basis for intelligent ship lock scheduling under congestion, energy, and resource constraints. Full article

Current detection technologies of operation current in power systems primarily rely on electromagnetic induction principles and infrared thermal imaging. These methods suffer from inherent limitations such as dependence on external power supplies, susceptibility to interference in complex electromagnetic environments, and high equipment costs. Electrochromic materials, which can directly convert electrical signals into optical signals and enable self-sensing without external power, offer a novel technological pathway for condition monitoring of electrical equipment. However, existing electrochromic materials still face technical challenges in power equipment operating environments, including high response thresholds, poor environmental stability, and short cycle life. Based on the synergistic electrochromic effect of poly(3-hexylthiophene) (P3HT) and fluoran, this study develops a color-changing coating suitable for operating current sensing. Core–shell structured microcapsules with urea-formaldehyde resin as the wall material were prepared via in situ polymerization to effectively encapsulate the P3HT–fluoran composite core material. These microcapsules were uniformly dispersed in an epoxy acrylate/TMPTA ultraviolet-curable resin system to form a current-sensing coating with excellent adhesion and insulation properties. Test results show that the coating, applied on a busbar, undergoes a noticeable color change from red to white within 30 s when a current of 100 A passes through the busbar, with a color difference (ΔE) of 25.3. The coating exhibits adhesion strength exceeding 11.7 MPa, volume resistivity on the order of 10¹³ Ω·m, and a breakdown field strength higher than 85 kV/mm. After 100 cycles, ΔE remains stable, demonstrating good cyclic durability. This research provides a new visual sensing solution for high-current monitoring and shows broad application prospects in the field of power equipment operation status monitoring. Full article

This study analyzed the effect of forming temperature on the roller hemming process of AA6011-T4 aluminum alloy sheets, using a 2^K factorial design to also evaluate the influence of roller diameter and flange height. A total of 24 experimental tests were conducted, varying the forming temperature (23 °C and 50 °C), roller diameter (22 mm and 50 mm), and flange height (7 mm and 10 mm). The hemming process was performed using a six-axis industrial robot (FANUC 2000i, Fanuc Corporation, Oshino, Japan) with roller tooling mounted o n a support fixture. The height of the flanged profile was measured using a coordinate measuring machine. ANOVA results, processed with MINITAB 18, showed that forming temperature, roller diameter, and flange height all have a statistically significant effect on the final profile height. No significant interactions were found among the factors, indicating their effects are independent. The most favorable configuration for maximizing profile height was the combination of the largest roller diameter and the highest flange height, under cold forming conditions. Additionally, a significant difference was observed between cold and warm forming processes in terms of the resulting profile height, highlighting the relevance of temperature control in the roller hemming of AA6011-T4 aluminum alloy. Full article

Colocasia kerrii Gagnep. has been treated as a synonym of C. fallax Schott in both the Flora of China and the Flora of Thailand accounts of Colocasia. However, detailed examination of the type material and additional specimens clearly demonstrates that C. kerrii is a distinct species. It can be readily distinguished from C. fallax and other species of Colocasia by the combination of the following characters: a spathe that is only strongly constricted between the spathe base and limb; a spathe limb reflexed and slightly coiled at staminate anthesis; a sessile or subsessile spadix; subsessile stigmas with very short styles; and a sterile zone between the pistillate and staminate zones nearly as long as the pistillate zone and covered with elongate, rhombo-hexagonal synandrodes. The specific status of C. kerrii is therefore reinstated. It is compared with the later described C. bicolor C.L.Long & L.M.Cao, which is here placed in synonymy. The name Colocasia kerrii Gagnep. is lectotypified, and an amended description, updated distribution data, ecological notes, and a preliminary IUCN conservation assessment are provided. Full article

Wild edible fruits play an important role in supporting food security, nutrition, and traditional knowledge systems in rural communities, yet their diversity and uses remain insufficiently documented in many parts of Thailand. This study aimed to investigate the diversity, utilization, and ethnobotanical significance of wild edible fruit species in Kut Chum District, Yasothon Province. Ethnobotanical data were collected through semi-structured interviews and field surveys with local informants, and quantitative indices, including the Cultural Importance Index (CI), Fidelity Level (%FL), and Informant Consensus Factor (ICF), were applied to evaluate species significance and medicinal agreement. A total of 71 species belonging to 33 families were recorded, with most species consumed as fresh fruits and a subset used for medicinal purposes. Several species, such as Irvingia malayana Oliv. ex A.W.Benn., Phyllanthus emblica L., and Syzygium cumini (L.) Skeels exhibited high cultural importance, reflecting their key roles in local diets. High ICF values across therapeutic categories indicated strong consensus in ethnomedicinal knowledge. Additionally, 44 species not used medicinally in the study area were reported as medicinal in other regions, highlighting spatial variation in knowledge systems. These findings emphasize the importance of wild edible fruits as multifunctional resources contributing to food and nutritional security. Integrating culturally important species into conservation and sustainable use strategies may support biodiversity preservation and the continuity of traditional ecological knowledge. Full article

This work explores the growing field of fractional calculus, with particular emphasis on the complexities and opportunities associated with variable-order derivatives. We critically assess existing definitions, identifying those that are consistent with the established principles of constant-order fractional calculus. Based on this analysis, we introduce new formulations derived from the Grünwald–Letnikov and Liouville approaches, together with a novel variable-order Mittag–Leffler function. The core of our study is devoted to investigating the existence and uniqueness of solutions for a coupled system of variable-order fractional differential equations subject to initial conditions. Using Schauder’s fixed-point theorem and the Banach contraction principle, we establish new results that contribute to strengthening the theoretical foundation of such dynamical systems. Full article

The global transition toward carbon-neutral energy solutions has established Solid Oxide Fuel Cells (SOFCs) as a key technology for next-generation power generation. This work presents a comprehensive numerical study and multi-factor statistical analysis of an anode-supported SOFC fueled by synthetic diesel. A three-dimensional computational fluid dynamics model, validated against experimental data, was integrated with a Taguchi L₂₇ orthogonal array to systematically evaluate the influence of six key parameters: temperature, fuel mass flow rate, operating pressure, current load, flow channel configuration, and methane molar fraction. Statistical analysis through the signal-to-noise ratio and analysis of variance identified the operating current as the most significant factor affecting cell voltage, followed by the fuel mass flow rate and temperature. The experiments showed that the highest levels of all factors (except for the current, which had the lowest level) maximize electrochemical performance while maintaining a steam-to-carbon ratio (S/C) within a range of 0.83 to 0.92, calculated based on total carbon content, ensuring sufficient humidification for internal reforming across all tested fuel compositions. Furthermore, a multiple linear regression model was developed as a computationally efficient surrogate, demonstrating exceptional predictive accuracy with an R² of 0.9954 and a mean relative error of 1.76% across independent validation cases. These results provide a robust methodology for rapid design and sensitivity analysis of internal-reforming SOFCs, offering a precise tool for optimizing fuel utilization in high-temperature electrochemical systems. Full article

As the power industry continues to advance rapidly, large-scale generators are evolving toward higher voltage levels and greater capacity. The heat accumulation associated with high voltage and large capacity accelerates the aging of the main insulation. It is necessary to enhance the thermal conductivity (λ) and dielectric properties of existing main insulation materials. This work focuses on investigating the effects of varying addition levels of two different-sized BN particles on the λ and dielectric properties of the mica tape composite dielectric. The experimental findings demonstrate a progressive enhancement in the λ of the mica tape corresponding to the incremental addition of h-BN concentration. When the doping concentration reaches 20 wt.%, the λ of the two h-BN-doped mica tape (h-BN/MT) reaches a maximum of 0.382 W/(m·K), 0.4 W/(m·K), respectively, which enhances the λ of the contrasting pure mica tape (0.199 W/(m·K)) by 91.95% and 101.01%, respectively. In terms of electrical insulation properties, both sizes of h-BN/MT perform well, with breakdown strength above 32 kV/mm. Furthermore, the second-order thermal conductivity model of mica tape doped with different sizes of h-BN was constructed by combining the Halpin–Tsai model with the Series model, which allows the calculation of λ of mica tape composites doped with different sizes of h-BN. This work provides a novel structural design approach for preparing mica tape composite dielectric that simultaneously exhibits high λ and high insulation properties. Full article

Quality evaluation in production systems represents a significant challenge in the manufacturing industry, particularly in environments where expert judgment plays a key role in managing the inherent uncertainty of the production system. This study proposes a fuzzy multicriteria decision-making control chart, termed Fuzzy Decision-Making Control Chart based on AHP-Extent and Triangular Fuzzy Numbers (FDMCC-AHPE). The method integrates expert knowledge through triangular fuzzy numbers and a Fuzzy Analytic Hierarchy Process supported by Extent Analysis, to define fuzzy decision intervals for quality assessment and subsequently perform a structured analysis to classify the product within a control chart framework. In this framework, expert judgments expressed through linguistic evaluations are systematically translated into triangular fuzzy numbers and processed using FAHP–Extent Analysis, allowing the aggregation of subjective assessments within a structured mathematical decision model. The proposed method was validated in a tannery company, specifically in the retanning process. The industrial case study considers both qualitative criteria, such as surface defects and color uniformity, and quantitative process variables that include bath pH, treatment duration, and processing temperature. The results were compared with an empirical expert-based evaluation and a structured expert assessment supported by a multicriteria decision-making method. The findings demonstrate that the FDMCC-AHPE exhibits greater sensitivity in discriminating between quality states under uncertain evaluation conditions, particularly when samples involve complex evaluation conditions. Full article