Tourism planners rely on accurate demand forecasting. However, despite numerous advancements, crucial methodological issues remain unaddressed. This study aims to further improve the modeling ...accuracy and advance the artificial intelligence (AI)-based tourism demand forecasting methods. Deep learning models that predict tourism demand are often highly complex and encounter overfitting, which is mainly caused by two underlying problems: (1) access to limited data volumes and (2) additional explanatory variable requirement. To address these issues, we use a decomposition method that achieves high accuracy in short- and long-term AI-based forecasting models. The proposed method effectively decomposes the data and increases accuracy without additional data requirement. In conclusion, this study alleviates the overfitting issue and provides a methodological contribution by proposing a highly accurate deep learning method for AI-based tourism demand modeling.
In order to solve the particle circulation problem of external circulation fluidized bed evaporator, a new particle circulation device was developed, and a cold experiment device was set up for ...reference to the principle of gassolid circulating fluidized bed U-loop seal valve. The adjustment characteristics of the particle circulation device were studied experimentally. The effects of different flow combinations on pressure drop, particle circulation rate and particle volume fraction of heat exchange tube were investigated when the main flow and any auxiliary flow of the sealing valve were combined. It was found that when the main flow rate is constant, the pressure drop of the heat exchange tube increases with the increase of the auxiliary flow rate, and the pressure drop trend is stable when the main flow and loose flow are combined. The flow rate of particle circulation can be adjusted by adjusting the flow rate of any auxiliary flow alone, and fluidized flow has the strongest ability to regulate the particle circulation rate. The amplitude of the power spectral density of the pressure differential fluctuation signal is related to the particle circulation rate and volume fraction, so the flow state in the pipe can be studied by this method.
The diversity and functionality of gut microbiota may play a crucial role in the function of human motor-related systems. In addition to traditional nutritional supplements, there is growing interest ...in microecologics due to their potential to enhance sports performance and facilitate post-exercise recovery by modulating the gut microecological environment. However, there is a lack of relevant reviews on this topic. This review provides a comprehensive overview of studies investigating the effects of various types of microecologics, such as probiotics, prebiotics, synbiotics, and postbiotics, on enhancing sports performance and facilitating post-exercise recovery by regulating energy metabolism, mitigating oxidative-stress-induced damage, modulating immune responses, and attenuating bone loss. Although further investigations are warranted to elucidate the underlying mechanisms through which microecologics exert their effects. In summary, this study aims to provide scientific evidence for the future development of microecologics in athletics.
The intestinal tract of humans harbors a dynamic and complex bacterial community known as the gut microbiota, which plays a crucial role in regulating functions such as metabolism and immunity in the ...human body. Numerous studies conducted in recent decades have also highlighted the significant potential of the gut microbiota in promoting human health. It is widely recognized that training and nutrition strategies are pivotal factors that allow athletes to achieve optimal performance. Consequently, there has been an increasing focus on whether training and dietary patterns influence sports performance through their impact on the gut microbiota. In this review, we aim to present the concept and primary functions of the gut microbiota, explore the relationship between exercise and the gut microbiota, and specifically examine the popular dietary patterns associated with athletes’ sports performance while considering their interaction with the gut microbiota. Finally, we discuss the potential mechanisms by which dietary patterns affect sports performance from a nutritional perspective, aiming to elucidate the intricate interplay among dietary patterns, the gut microbiota, and sports performance. We have found that the precise application of specific dietary patterns (ketogenic diet, plant-based diet, high-protein diet, Mediterranean diet, and high intake of carbohydrate) can improve vascular function and reduce the risk of illness in health promotion, etc., as well as promoting recovery and controlling weight with regard to improving sports performance, etc. In conclusion, although it can be inferred that certain aspects of an athlete’s ability may benefit from specific dietary patterns mediated by the gut microbiota to some extent, further high-quality clinical studies are warranted to substantiate these claims and elucidate the underlying mechanisms.
Objective To investigate the association between the weight-adjusted-waist index (WWI) and cognitive decline in elderly Americans from 2011 to 2014. Methods A cross-sectional study was conducted on ...2,762 elderly participants from the National Health and Nutrition Examination (NHANES) between 2011 and 2014. WWI was calculated by dividing waist circumference (cm) by the square root of body weight (kg). Participants assessed their cognitive functions using tests such as the DSST, AFT, and CERAD W-L. In this research, multiple logistic regression, HIA, limited cubic spline (RCS), and threshold effect analysis methods were utilized to explore the relationship between cognitive decline and WWI. Results The study involved 2,762 participants aged 60 years and older, comprising 1,353 males (49%) and 1,409 females (51%), with a median age of 69.3 years (standard deviation = 6.7). The analysis revealed that the risk of cognitive decline was positively associated with the WWI. Fully adjusted models indicated significant correlations with the CERAD W-L odds ratio (OR) = 1.24, 95% confidence interval (CI) = 1.06–1.46, p < 0.008, AFT (OR = 1.27, 95% CI = 1.08–1.49, p = 0.003), and DSST (OR = 1.56, 95% CI = 1.29–1.9, p < 0.001). Subgroup analysis demonstrated a consistent relationship across different population settings except for gender (average of interactions, p > 0.05). A J-shaped relationship between WWI and low DSST scores was observed using multivariate restricted cubic spline (RCS) regression ( P for non-linearity <0.05), with the curve steepening when WWI ≥ 12.21 cm/√kg. Additionally, the study found that WWI was more strongly associated with an increased risk of cognitive decline than other obesity indicators such as Body Mass Index (BMI), waist circumference (WC), and A Body Shape Index (ABSI). Conclusion Our data have shown a significant positive association between the WWI and a higher risk of cognitive decline in older Americans, with a J-shaped non-linear relationship between WWI and DSST. In addition, our findings indicate that WWI was associated with greater cognitive decline than other markers of obesity.
Intrusion Detection Systems (IDSs) utilise deep learning techniques to identify intrusions with maximum accuracy and reduce false alarm rates. The feature extraction is also automated in these ...techniques. In this paper, an ensemble of different Deep Neural Network (DNN) models like MultiLayer Perceptron (MLP), BackPropagation Network (BPN) and Long Short Term Memory (LSTM) are stacked to build a robust anomaly detection model. The performance of the ensemble model is analysed on different datasets, namely UNSW-NB15 and a campus generated dataset named VIT_SPARC20. Other types of traffic, namely unencrypted normal traffic, normal encrypted traffic, encrypted and unencrypted malicious traffic, are captured in the VIT_SPARC20 dataset. Encrypted normal and malicious traffic of VIT_SPARC20 is categorised by the deep learning models without decrypting its contents, thus preserving the confidentiality and integrity of the data transmitted. XGBoost integrates the results of each deep learning model to achieve higher accuracy. From experimental analysis, it is inferred that UNSW_ NB results in a maximal accuracy of 99.5%. The performance of VIT_SPARC20 in terms of accuracy, precision and recall are 99.4%. 98% and 97%, respectively.
Advances in tourism demand forecasting immensely benefit tourism and other sectors, such as economic and resource management studies. However, even for novel AI-based methodologies, the challenge of ...limited available data causing model overfitting and high complexity in forecasting models remains a major problem. This study proposes a novel group-pooling-based deep-learning model (GP–DLM) to address these problems and improve model accuracy. Specifically, with our group-pooling method, we advance the tourism forecasting literature with the following findings. First, GP–DLM provides superior accuracy in comparison with benchmark models. Second, we define the novel dynamic time warping (DTW) clustering quantitative approach. Third, we reveal cross-region factors that influence travel demands of the studied regions, including “travel blog,” “best food,” and “Air Asia.”
•Our AI-based deep-learning approach contributes to higher forecasting accuracy.•Our innovative deep-learning model alleviates the limited data availability.•With our new pooling method, we significantly reduce model overfitting.•We reveal similar cross-country demand patterns for the Asia-Pacific regions.
•The film thickness of the corrugated tube increased with the increasing of both film Reynolds number and was the thinnest β = 90°−120°.•The film thickness of the corrugated tube decreased when the ...tube spacing increases or the tube diameter/ corrugated radius decreases.•The falling film thickness was thinner at the wave crests and thicker at the wave troughs.•The phenomenon of dryout hardly appears in the falling film flow of the corrugated tube.•A new correlation has been given to predict the falling film thickness of the horizontal corrugated tube.
Falling-film evaporation has an essential method for desalination. The heat transfer tube is the core component of falling film evaporator. Liquid film thickness is one of the most important parameters for predicting heat and mass transfer coefficient of falling film evaporation. In this paper, a set of experimental apparatus for measuring the film thickness of a horizontal tube is set up. The experiments have been undertaken under different parameters, i.e. the tube diameter varying from 25 to 45 mm, the tube spacing ranging from 10 to 60 mm, the corrugated radius varying from 0.25 to 1 mm, and the film Reynolds number ranging from 150 to 1000. The liquid film falling around a horizontal tube is performed to explore the distribution characteristics of the film thickness. The liquid film thickness is measured by the conductance probe measurement method. The experimental results showed that the film thickness of the corrugated tube increases with the increasing of the film Reynolds number, which is the thinnest from 90° to 120°. It decreases as the tube spacing increases and increases with the tube diameter and corrugated radius. The liquid in the wave troughs can be replenished to the wave crests at any time because of the corrugated structure. The falling film thickness was thinner at the wave crests and thicker at the wave troughs. The phenomenon of dryout hardly appears in the falling film flow of the corrugated tube. Based on the experimental data, a new correlation has been given to predict the film thickness of the corrugated tube.
Abstract Large scale categorical datasets are ubiquitous in machine learning and the success of most deployed machine learning models rely on how effectively the features are engineered. For ...large-scale datasets, parametric methods are generally used, among which three strategies for feature engineering are quite common. The first strategy focuses on managing the breadth (or width) of a network, e.g., generalized linear models (aka. ). The second strategy focuses on the depth of a network, e.g., Artificial Neural networks or (aka. ). The third strategy relies on factorizing the interaction terms, e.g., Factorization Machines (aka. ). Each of these strategies brings its own advantages and disadvantages. Recently, it has been shown that for categorical data, combination of various strategies leads to excellent results. For example, -Learning, , etc., leads to state-of-the-art results. Following the trend, in this work, we have proposed another learning framework—-Learning, based on the combination of , , , and a newly introduced component named (). is in the form of a Bayesian network classifier whose structure is learned apriori, and parameters are learned by optimizing a joint objective function along with , and parts. We denote the learning of parameters as . Additionally, the parameters of are constrained to be actual probabilities—therefore, it is extremely interpretable. Furthermore, one can sample or generate data from , which can facilitate learning and provides a framework for knowledge-guided machine learning . We demonstrate that our proposed framework possesses the resilience to maintain excellent classification performance when confronted with biased datasets. We evaluate the efficacy of our framework in terms of classification performance on various benchmark large-scale categorical datasets and compare against state-of-the-art methods. It is shown that, framework (a) exhibits superior performance on classification tasks, (b) boasts outstanding interpretability and (c) demonstrates exceptional resilience and effectiveness in scenarios involving skewed distributions.