Search Results (1,691)

In recent years, computational intelligence techniques have significantly contributed to the automation and optimization of trading strategies. Despite the increasing sophistication of predictive models, classical technical indicators such as dual Simple Moving Averages (2-SMA) remain popular due to their simplicity and interpretability. This work proposes an adaptive trading system that combines the 2-SMA strategy with a learning-based metaheuristic optimizer known as the Learning-Based Linear Balancer ($L{B}^2$). The objective is to dynamically adjust the strategy’s parameters to maximize returns in the highly volatile cryptocurrency market. The proposed system is evaluated through simulations using historical data of the BTCUSDT futures contract from the Binance platform, incorporating real-world trading constraints such as transaction fees. The optimization process is validated over 34 training/test splits using overlapping 60-day windows. Results show that the $L{B}^2$-optimized strategy achieves an average return on investment (ROI) of 7.9% in unseen test periods, with a maximum ROI of 17.2% in the best case. Statistical analysis using the Wilcoxon Signed-Rank Test confirms that our approach significantly outperforms classical benchmarks, including Buy and Hold, Random Walk, and non-optimized 2-SMA. This study demonstrates that hybrid strategies combining classical indicators with adaptive optimization can achieve robust and consistent returns, making them a viable alternative to more complex predictive models in crypto-based financial environments. Full article

Contemporary construction faces the need to reduce its negative impact on the environment, prompting designers, investors, and contractors to seek more sustainable materials and technologies. One area of dynamic development is the use of natural fibers as an alternative to conventional, often synthetic, building components. Plant- and animal-based fibers, such as hemp, flax, jute, straw, bamboo, and sheep’s wool, are characterized by low energy consumption in production, renewability, and biodegradability. Their use is in line with the concept of a circular economy and reduces the carbon footprint of buildings. Natural fibers offer a number of beneficial physical and functional properties, including good thermal and acoustic insulation parameters, as well as hygroscopicity, which allows for the regulation of indoor humidity, improving air quality and comfort of use. In recent years, there has also been a renaissance of traditional building techniques, such as straw construction, often combined with modern engineering standards. Their potential is particularly recognized in green and energy-efficient construction. The article provides an overview of the types of natural fibers available for use in construction and analyzes their technical, environmental, and economic properties. It also draws attention to current regulations, standards, and certifications (e.g., LEED, BREEAM) that promote the popularization of these solutions. In light of the analyzed data, the role of natural fibers as a viable alternative supporting the transformation of the construction sector towards sustainable development is considered. Full article

Recommender systems on digital platforms profoundly influence user behavior through content dissemination, and their diffusion process is similar to the spreading mechanism of infectious diseases to some extent. In this paper, we use a network-based susceptibility-infection (SI) model to model the propagation dynamics of recommended content, and systematically compare the differences in propagation efficiency among three recommendation strategies based on popularity, collaborative filtering, and content. We constructed scale-free user networks based on real-world clickstream data and dynamically adapted the SI model to reflect the realistic scenario of user engagement decay over time. To enhance the understanding of the recommendation process, we further simulate the visualization changes of the propagation process to show how the content spreads among users. The experimental results show that collaborative filtering performs superior in the initial dissemination, but its dissemination effect decays rapidly over time and is weaker than the other two methods. This study provides new ideas for modeling and understanding recommender systems from an epidemiological perspective. Full article

Soil moisture or moisture content is a fundamental constituent of the hydrological system of the Earth and its ecological systems, playing a pivotal role in the productivity of agricultural produce, climate modeling, and water resource management. This review comprehensively examines conventional and advanced approaches for estimation or measuring of soil moisture, including in situ methods, remote sensing technologies, UAV-based monitoring, and machine learning-driven models. Emphasis is primarily on the evolution of soil moisture measurement from destructive gravimetric techniques to non-invasive, high-resolution sensing systems. The paper emphasizes how machine learning modules like Random Forest models, support vector machines, and AI-based neural networks are becoming more and more popular for modeling intricate soil moisture dynamics with data from several sources. A bibliometric analysis further underscores the research trends and identifies key contributors, regions, and technologies in this domain. The findings advocate for the integration of physics-based understanding, sensor technologies, and data-driven approaches to enhance prediction accuracy, spatiotemporal coverage, and decision-making capabilities. Full article

Chrysanthemum morifolium Ramat. is an important ornamental plant, holding dual economic value as a medicinal and edible plant. Jinsi Huangju is a popular healthy tea drink prepared from the large and elegant shaped flowers of C. morifolium. However, the suboptimal accumulation of bioactive flavonoids during conventional harvest (full bloom stage) limits its commercial potential. To elucidate the molecular mechanisms governing flavonoid biosynthesis in Jinsi Huangju flowers and identify key genetic regulators for metabolic engineering, we performed integrated metabolomic and transcriptomic analyses of flowers at distinct developmental stages using ultra-performance liquid chromatography–tandem mass spectrometry (UPLC-MS/MS) and RNA-seq. Differential metabolites were screened, and candidate genes were validated via transient transformation assays. Among 2146 identified metabolites, flavonoids were the predominant differential compounds, with accumulation patterns being strongly stage dependent. Thirty-eight flavonoid biosynthetic genes and key transcription factors from the MYB, bHLH, and WD40 families exhibited dynamic expression. The CmMYB8a was confirmed as a positive regulator of flavonoid biosynthesis through transient overexpression. This study deciphers the stage-specific flavonoid accumulation in Jinsi Huangju and identifies CmMYB8a as a pivotal regulatory target. Our findings provide genetic resources for breeding high-flavonoid cultivars via molecular design. Full article

Natural fiber-reinforced polymers are gaining popularity as sustainable structural materials. However, their inherent variability can limit their reliability in load-bearing applications. To address this issue, we investigate a novel structural health monitoring method that leverages mechanoelectrical effects in flax fiber-reinforced epoxy composites. In our study, a contactless capacitive coupled measurement setup records electrical polarization during fatigue testing at four load levels. The polarization signals we observed increased with increasing load levels. Additionally, changes in polarization correlate with changes in dynamic modulus, providing early indicators of potential failure. This work lays the foundation for a new type of structural health monitoring in natural fiber-reinforced polymers. Full article

High-quality disease segmentation plays a crucial role in the precise identification of rice diseases. Although the existing deep learning methods can identify the disease on rice leaves to a certain extent, these methods often face challenges in dealing with multi-scale disease spots and irregularly growing disease spots. In order to solve the challenges of rice leaf disease segmentation, we propose KBNet, a novel multi-modal framework integrating language and visual features for rice disease segmentation, leveraging the complementary strengths of CNN and Transformer architectures. Firstly, we propose the Kalman Filter Enhanced Kolmogorov–Arnold Networks (KF-KAN) module, which combines the modeling ability of KANs for nonlinear features and the dynamic update mechanism of the Kalman filter to achieve accurate extraction and fusion of multi-scale lesion information. Secondly, we introduce the Boundary-Constrained Physical-Information Neural Network (BC-PINN) module, which embeds the physical priors, such as the growth law of the lesion, into the loss function to strengthen the modeling of irregular lesions. At the same time, through the boundary punishment mechanism, the accuracy of edge segmentation is further improved and the overall segmentation effect is optimized. The experimental results show that the KBNet framework demonstrates solid performance in handling complex and diverse rice disease segmentation tasks and provides key technical support for disease identification, prevention, and control in intelligent agriculture. This method has good popularization value and broad application potential in agricultural intelligent monitoring and management. Full article

Freemium, a popular business model in the digital economy, offers a basic product for free while charging for advanced features or value-added services. This pricing strategy enables platforms to attract a broad user base and then monetize through premium offerings. Customer characteristics and service price are important factors affecting customer choice behavior in such a model. Based on consumption stickiness, we consider a monopoly that provides value-added services by incorporating a multinomial logit model into a two-stage dynamic pricing model. First, we analyze the optimal pricing of value-added services under a normal sales scenario. We then consider optimal pricing during the marketing period under two strategies—level improvement for value-added services and quality reduction for a basic product—and analyze the applicability of each. The results show that increasing the value-added service level has a positive effect on the optimal price of value-added services, whereas reducing the basic product quality has no effect on the optimal price. Furthermore, the numerical simulation shows that when the depth of consumer stickiness is low, the optimal marketing strategy reduces the quality of the basic product, the price of value-added services should be higher than that in the normal sales period but lower than the price under the level-improvement strategy for value-added services; otherwise, improving the level of the value-added services becomes the optimal approach. This study provides a theoretical basis and decision support for product quality design and service pricing that applies to freemium platforms. Full article

With the popularization of social media, information related to public health events has seen explosive growth online, making it essential to accurately identify informative tweets with decision-making and management value for public health emergency response and risk monitoring. However, existing methods often suffer performance degradation during cross-event transfer due to differences in data distribution, and research specifically targeting public health events remains limited. To address this, we propose the Label Confusion Domain Adversarial Network (LCDAN), which innovatively integrates label confusion with domain adaptation to enhance the detection of informative tweets across different public health events. First, LCDAN employs an adversarial domain adaptation model to learn cross-domain feature representation. Second, it dynamically evaluates the importance of different source domain samples to the target domain through label confusion to optimize the migration effect. Experiments were conducted on datasets related to COVID-19, Ebola disease, and Middle East Respiratory Syndrome public health events. The results demonstrate that LCDAN significantly outperforms existing methods across all tasks. This research provides an effective tool for information detection during public health emergencies, with substantial theoretical and practical implications. Full article

Fish coloration plays an important role in reproduction and camouflage, yet capturing color variation under field conditions remains challenging. We present a standardized, semi-automated protocol for measuring body coloration in the popular model fish threespine stickleback (Gasterosteus aculeatus). Individuals are photographed in a controlled light box within minutes of capture, and color is sampled from eight anatomically defined standard sites in human-perception-based CIELAB space. Analyses combine univariate color metrics, multivariate statistics, and the ΔE* perceptual difference index to detect subtle shifts in hue and brightness. Validation on pre-spawning fish shows the method reliably distinguishes males and females well before full breeding colors develop. Although it currently omits ultraviolet signals and fine-scale patterning, the approach scales efficiently to large sample sizes and varying lighting conditions, making it well suited for population-level surveys of camouflage dynamics, sexual dimorphism, and environmental influences on coloration in sticklebacks. Full article

News recommendation systems must simultaneously address multiple challenges, including dynamic user interest modeling, nonlinear popularity patterns, and diversity recommendation in cold-start scenarios. We present a Popularity-Aware Dynamic Multi-Perspective Fusion Network (PAD-MPFN) that innovatively integrates three key components: adaptive subspace projection for multi-source interest fusion, logarithmic time-decay factors for popularity bias mitigation, and dynamic gating mechanisms for personalized recommendation weighting. The framework uniquely combines sequential behavior analysis, social graph propagation, and temporal popularity modeling through a unified architecture. Experimental results on the MIND dataset, an open-source version of MSN News, demonstrate that PAD-MPFN outperforms existing methods in terms of recommendation performance and cold-start scenarios while effectively alleviating information overload. This study offers a new solution for dynamic interest modeling and diverse recommendation. Full article

Drones can improve the efficiency of point-to-point logistics and distribution and reduce labor costs; however, the complex three-dimensional airspace environment poses significant challenges for flight paths. To address this demand, this paper proposes a hybrid algorithm that integrates the Sparrow Search Algorithm (SSA) with the African Vulture Optimization Algorithm (AVOA). Firstly, the algorithm introduces Sobol sequences at the population initialization stage to optimize the initial population; then, we incorporate SSA’s discoverer and vigilant mechanisms to balance exploration and exploitation and enhance global exploration capabilities; finally, multi-guide differencing and dynamic rotation transformation strategies are introduced in the first exploitation phase to enhance the direction of local exploitation by fusing multiple pieces of information; the second exploitation phase achieved a dynamic balance between elite guidance and population diversity through adaptive weight adjustment and enhanced Lévy flight strategy. In this paper, a three-dimensional model is built under a variety of constraints, and SAVOA (Sparrow-Enhanced African Vulture Optimization Algorithm) is compared with a variety of popular algorithms in simulation experiments. SAVOA achieves the optimal path in all scenarios, verifying the efficiency and superiority of the algorithm in UAV logistics path planning. Full article

Thermovinification has emerged as a rising alternative method in red wine production, gaining popularity among winemakers. The use of autochthonous yeasts isolated from grapes is also an interesting practice that contributes to the creation of wine with a distinctive regional character. This research investigated how combining thermovinification with autochthonous yeast strains influences the fermentation dynamics of Syrah wine. Six treatments were conducted, combining the use of commercial and two autochthonous yeasts with traditional vinification (7-day maceration) and thermovinification (65 °C for 2 h) processes. Sugars and alcohols were quantified during alcoholic fermentation by high-performance liquid chromatography with refractive index detection. Cell viability and kinetic parameters, such as ethanol formation rate and sugar consumption, were also evaluated. The Syrah wine’s composition was characterized by classical wine analyses (OIV procedures). The results showed that cell viability was unaffected by thermovinification. Thermovinification associated with autochthonous yeasts improved the efficiency of alcoholic fermentation. Thermovinified wines also yielded a higher alcohol content (13.9%). Future studies should investigate how thermovinification associated with autochthonous yeasts affects the metabolomic and flavoromic properties of Syrah wine and product acceptability. Full article

Many kinds of panel structures are proposed in aircraft design. This study presents a topology optimization method to improve the buckling resistance of panel structures. It should be noted that a popular configuration of the present panel structure is that with ribs and frames. Stiffening characteristics (i.e., effects of increasing structural stiffness of a panel structure with ribs and frames) are thus included during analysis of panel structures. After studying the coupling relationship between the dynamic characteristics and buckling behavior of the panel, a developed MMC (moving morphable component) method is proposed for topology optimization to improve the buckling resistance of the panel. It is seen that the coupling relationship between the dynamic characteristics and buckling behavior of the panel is mainly reflected when the compression force acts on the panel, corresponding that dynamic characteristics will vary with the load. If the load acts on the structure, the first-order natural frequency of the panel with ribs and frames in this study decreases with the increase in the load, with the optimization objective of maximizing the first-order natural frequency. Based on the coupling relationship between dynamic characteristics and buckling behavior, the critical buckling load of the panel increases as the first-order natural frequency increases. The present optimization method can reduce computational complexity without changing the accuracy of the calculation. At the same time, the coupling relationship between dynamic characteristics and buckling behavior is applied in topology optimization, which is of great significance to improve the comprehensive performance of panel structures in the engineering design process. This paper improves the dynamic characteristics and buckling resistance of panels with ribs and frames based on the improved MMC method. The proposed method effectively meets the design requirements of flight vehicle design in complex environments. Full article

The integration of urban bus and subway services is critical for attracting passengers and for the sustainable development of public transit, as it helps to boost ridership with an extensive service that combines the attractions of buses and subways. To identify barriers in transferring from bus to subway or vice versa at different periods of the day, this research develops the popular evaluation indices found in the literature and revises them to reflect the most critical attributes of transfer quality. Thus, the deficiencies of transferring from subway to bus or vice versa are independently examined. Motivated by the changes in the indices at different periods, the day is divided into multiple periods. Then, dynamic transfer-volume-based TOPSIS is developed, instead of assigning index weights based on period sequence. The index weight is revised to emphasize the peak periods. Taking a case study in Suzhou, the barriers to inter-modal transfer are identified between subways and buses. It is found that subway-to-bus transfer quality is only one-third of that of bus-to-subway transfers due to the great changes in bus runs (19–45 vs. 14–26), lower bus coverage rates (0.42–0.47 vs. 0.50–0.55), and larger deviation of connected POIs (9.0–9.4 vs. 1.1–1.8), as well as the lower reliability of connected bus lines (0.3–0.47 beyond peaks vs. 0.58 and 0.96). Multi-faceted implementations are recommended for inter-modal subway-to-bus transfers and bus-to-subway transfers, respectively. The research provides insights on enhancing bus–subway transfer quality with finer detail into different periods, to encourage the loyalty of transit passengers with more stable and reliable bus as well as transit service. Full article