Suchergebnisse

Introduction: The aim of the research was to analyze the - Introduced in 2015 as a new force protection capability - Hungarian Defence Forces Body Composition Program (HDF BCP) participants' pattern of the measurement parameters and their relationship to each other, furthermore, to create a measurement protocol that can be used with large number of elements, which allows the estimation of strength and fat-free mass in the following.Methods: The examination was carried out between 2017 and 2020. Within the HDF BCP, the measured and estimated parameters of 283 volunteers between the ages of 18 and 67 years old. A total of 709 measures were made. A Premium Body Impedance Analyzer 500 (BIA) instrument was used for the examinations. In addition, a DYNA 16 strength meter (DYNA) was used which makes it possible to measure the grip strength of both hands at the same time. Statistical calculations are performed with R-Studio program.Results: An increase in the phase angle is accompanied by an increase in the maximum hand grip strength (p < 0.001). The full body strength increases with weight gain regarding both sexes in all age groups tested (p < 0.001). Our linear regression model is suitable for estimating maximum hand grip strength using body weight, fat-free mass, age, and gender values (R2 = 0,74) and to estimate fat-free mass percentage based on body weight, maximum hand grip strength, and gender values (R2 = 0,78).Conclusion: The use of phase angle is an important indicator of a lifestyle change program. In the created linear regression model we will be able to estimate body fraction in significant numbers with high accuracy after measuring minimum parameters.

Abstract
Background
Precisely predicting the water levels of rivers is critical for planning and supporting flood hazard and risk assessments and maintaining navigation, irrigation, and water withdrawal for urban areas and industry. In Hungary, the water level of rivers has been recorded since the early nineteenth century, and various water level prediction methods were developed. The Discrete Linear Cascade Model (DLCM) has been used since 1980s. However, its performance is not always reliable under the current climate-driven hydrological changes. Therefore, we aimed to test machine learning algorithms to make 7-day ahead forecasts, choose the best-performing model, and compare it with the actual DLCM.

Results
According to the results, the Long Short-Term Memory (LSTM) model provided the best results in all time horizons, giving more precise predictions than the Baseline model, the Linear or Multilayer Perceptron Model. Despite underestimating water levels, the validation of the LSTM model revealed that 68.5‒76.1% of predictions fall within the required precision intervals. Predictions were relatively accurate for low (≤ 239 cm) and flood stages (≥ 650 cm), but became less reliable for medium stages (240–649 cm).

Conclusions
The LSTM model provided better results in all hydrological situations than the DLCM. Though, LSTM is not a novel concept, its encoder–decoder architecture is the best option for solving multi-horizon forecasting problems (or "Many-to-Many" problems), and it can be trained effectively on vast volumes of data. Thus, we recommend testing the LSTM model in similar hydrological conditions (e.g., lowland, medium-sized river with low slope and mobile channel) to get reliable water level forecasts under the rapidly changing climate and various human impacts.

Graphical Abstract