RESUMO
As the economy continues to develop and technology advances, there is an increasing societal need for an environmentally friendly ecosystem. Consequently, natural gas, known for its minimal greenhouse gas emissions, has been widely adopted as a clean energy alternative. The accurate prediction of short-term natural gas demand poses a significant challenge within this context, as precise forecasts have important implications for gas dispatch and pipeline safety. The incorporation of intelligent algorithms into prediction methodologies has resulted in notable progress in recent times. Nevertheless, certain limitations persist. However, there exist certain limitations, including the tendency to easily fall into local optimization and inadequate search capability. To address the challenge of accurately predicting daily natural gas loads, we propose a novel methodology that integrates the adaptive particle swarm optimization algorithm, attention mechanism, and bidirectional long short-term memory (BiLSTM) neural networks. The initial step involves utilizing the BiLSTM network to conduct bidirectional data learning. Following this, the attention mechanism is employed to calculate the weights of the hidden layer in the BiLSTM, with a specific focus on weight distribution. Lastly, the adaptive particle swarm optimization algorithm is utilized to comprehensively optimize and design the network structure, initial learning rate, and learning rounds of the BiLSTM network model, thereby enhancing the accuracy of the model. The findings revealed that the combined model achieved a mean absolute percentage error (MAPE) of 0.90% and a coefficient of determination (R2) of 0.99. These results surpassed those of the other comparative models, demonstrating superior prediction accuracy, as well as exhibiting favorable generalization and prediction stability.
RESUMO
Background: The levels of oxidative stress and proinflammatory factors in perimenopausal females increased, and they were also deeply troubled by insomnia. The occurrence of insomnia is related to the changes of oxidative stress and inflammation levels in the body. Perimenopausal insomnia may be related to mild systemic inflammation, and oxidative stress can promote chronic inflammation. However, the underlying mechanism behind the phenomenon is still unclear. Objective: The aim was to investigate whether the occurrence of perimenopausal insomnia disorder is related to higher levels of oxidative stress and inflammation in the body, and to explore the role of inducible nitric oxide synthase (iNOS) in perimenopausal insomnia. Methods: A total of 127 perimenopausal participants were recruited in this study. Participants with global scores of the Pittsburgh sleep quality index (PSQI) >7 were diagnosed with insomnia (n = 54). The patient health questionnaire-9 (PHQ-9) and generalized anxiety disorder-7 (GAD-7) were evaluated, and sociodemographic data were obtained. The serum concentrations of iNOS, interleukin 6 (IL6), and tumor necrosis factor α (TNFα) were measured using commercial assays. Results: In the insomnia group, IL6 levels were positively correlated with scores of component 5 and component 7 of PSQI, respectively. PHQ-9 and GAD-7 were positively correlated with the global score of PSQI component 7 and PSQI, respectively; PHQ-9 was positively correlated with the global score of PSQI component 1. Finally, PHQ-9, iNOS, and IL6 were found to be independent predictors of perimenopausal insomnia using logistic regression. Conclusions: Moderate oxidative stress caused by a certain concentration of iNOS plays a protective role in perimenopausal insomnia, while proinflammation and depression are potential risk factors.