Search

In recent years, the rapid growth of vehicles has imposed a significant burden on urban road resources. To alleviate urban traffic congestion in intelligent transportation systems (ITS), real-time and accurate traffic flow prediction has emerged as an effective approach. However, selecting relevant parameters from traffic flow information and adjusting hyperparameters in intelligent algorithms to achieve high prediction accuracy is a time-consuming process, posing practical challenges in dynamically changing traffic conditions. To address these challenges, this paper introduces a novel prediction architecture called Multiple Variables Heuristic Selection Long Short-Term Memory (MVHS-LSTM). The key innovation lies in its ability to select informative parameters, eliminating unnecessary factors to reduce computational costs while achieving a balance between prediction performance and computing efficiency. The MVHS-LSTM model employs the Ordinary Least Squares (OLS) method to intelligently reduce factors and optimize cost efficiency. Additionally, it dynamically selects hyperparameters through a heuristic iteration process involving epoch, learning rate, and window length, ensuring adaptability and improved accuracy. Extensive simulations were conducted using real traffic flow data from Shanghai to evaluate the enhanced performance of MVHS-LSTM. The prediction results were compared with those of the ARIMA, SVM, and PSO-LSTM models, demonstrating the innovative capabilities and advantages of the proposed model. [ABSTRACT FROM AUTHOR]

Objective This study was designed to evaluate the prevalence of thyroid nodules (TNs) and its relationship with urine iodine concentrations (UICs) after the regional rapid economic growth and lifestyle changes. Methods A cross-sectional survey was conducted in the general population aged 15-69 years. A questionnaire regarding general and personal characteristics and relevant information was administered. Ultrasonography of the thyroid was performed, and serum triiodothyronine (T3), tetraiodothyronine (T4), serum thyroid stimulating hormone (TSH), free triiodothyronine (FT3), free tetraiodothyronine (FT4), thyroglobulin antibody (TgAb), thyroid peroxidase antibody (TPOAb), and TSH receptor antibody (TRAb) levels were measured for each individual subject. Results The prevalence rates of TNs in the whole population, females and males were 27.76%, 34.04%, and 21.60%, respectively. The prevalence of multiple nodules increased with age, whereas the prevalence peaks differed between males and females. The median UICs in the whole population and females with non-TNs were higher than those of subjects with TNs ( P =0.0035, P =0.0068). The median UICs in subjects with a single TN were higher than those in subjects with multiple TNs ( P =0.0164, P =0.0127). The result showed a U-shaped curve relationship between UIC and prevalence of TNs. The prevalence of TNs was the lowest when the UIC was 140-400 μg/L. Conclusion The prevalence of TNs was nearly 30% and increased with age. The relationship between UIC and prevalence of TNs is U-shaped, with an increase in risk when the UIC was <140 μg/L and >400 μg/L. Very low or high UIC levels need attention and correction. [ABSTRACT FROM AUTHOR]