Adaptive neuro-fuzzy prediction of the optimum parameters of protective spur dike

This study proposes a new approach for determining the optimum dimensions of a protective spur dike to mitigate the amount of scour around existing spur dikes. Several parameters of a protective spur dike were studied to determine their optimum values, including length, angle, and distance. Also the effect of changes of flow intensity and sediment size were examined. The main objective of this article was to predict the optimum values of protective spur dikes to attain the best performance. To predict the parameters of protective spur dikes for controlling the scour around spur dikes, we used the adaptive neuro-fuzzy inference system method to construct a process that simulates the optimal parameters of a protective spur dike, including the actual length of the protective spur dike, the actual length of the main spur dikes, the distance between the protective spur dike and the first spur dike, the angle between the protective spur dike and the direction of flow, the intensity of the flow, and median size of the bed sediments. This intelligent estimator was implemented using MATLAB/Simulink, and the performances were investigated. The simulation results presented in this paper show the effectiveness of the developed method.     

Human mortality impacts of the 2015 summer heat spells in Slovakia

In 2015, Central Europe experienced an unusually warm summer season. For a great majority of climatic stations around Slovakia, it had been the warmest summer ever recorded over their entire instrumental observation period. In this study, we investigate the mortality effects of hot days’ sequences during that particular summer on the Slovak population. In consideration of the range of available mortality data, the position of 2015 is analysed within the years 1996–2015. Over the given 20-year period, the summer heat spells of 2015 were by far the most severe from a meteorological point of view, and clearly the deadliest with the total of almost 540 excess deaths. In terms of impacts, an extraordinary 10-day August heat spell was especially remarkable. The massive lethal effects of heat would have likely been even more serious under normal circumstances, since the number of premature deaths appeared to be partially reduced due to a non-standard mortality pattern in the first quarter of the year. The heat spells of the extremely warm summer of 2015 in Slovakia are notable not just for their short-term response in mortality. It appears that in a combination with the preceding strong influenza season, they subsequently affected mortality conditions in the country in the following months up until the end of the year. The impacts described above were rather different for selected population subgroups (men and women, the elderly). Both separately and as a part of the annual mortality cycle, the 2015 summer heat spells may represent a particularly valuable source of information for public health.     

Adaptive neuro-fuzzy selection of the optimal parameters of protective spur dike

This study proposes a new approach for determining optimum dimensions of protective spur dike to mitigate scour amount around existing spur dikes. The main objective of this article was to predict the most optimum values of the protective spur dikes to reach the best performance. To predict the protective spur dike parameters for scour controlling around spur dikes, this paper constructed a process which selects the optimal protective spur dike parameters in regard to actual length of the protective spur dike, actual length of the main spur dikes, distance between the protective spur dike and the first spur dike, angle between protective spur dike and flow direction, flow intensity and median size of bed sediments with adaptive neuro-fuzzy (ANFIS) method. To build a protective spur dike with the best features, it is desirable to select and analyze factors that are truly relevant or the most influential to the spur dike. This procedure is typically called variable selection, and it corresponds to finding a subset of the full set of recorded variables that exhibits good predictive abilities. In this study, architecture for modeling complex systems in function approximation and regression was used, based on using ANFIS. Variable searching using the ANFIS network was performed to determine how the five factors affect the protective spur dike. Experimental model of the protective spur dike was used to generate training and checking data for the ANFIS network.     

Adaptation of ANFIS model to assess thermal comfort of an urban square in moderate and dry climate

Attractiveness of the open urban spaces, such as plazas or squares, depends on the visitor’s thermal comfort. In this respect, it is important to assess the environment of such open space along with the demographic factors of the visitors. This study used the soft-computing method of adaptive neuro fuzzy inference system (ANFIS) to investigate the thermal comfort of visitors at a public square in Iran during hot and cold weather conditions. The ANFIS process for variable selection was implemented in order to detect the predominant variables affecting the individual’s comfortable feeling. Model’s training and testing data were collected through the field measurement and survey during hot and cold times of the year. We used 18 input parameters, representative of demographic and environmental factors, to compute visitor’s thermal sensation, comfort feeling, and 4 common indices, namely the mean radiant temperature (T_mrt), mean physiological equivalent temperature (PET), standard effective temperature (SET) and predicted mean vote (PMV). The results indicated that among the examined factors, the air temperature (T_a) is the most influential parameter and best predictor of accuracy for the individual’s comfort feeling at the studied urban square. The results show that T_a can best predict the common indices of outdoor comfort, namely the PMV, PET, SET, thermal sensation, T_mrt, and comfortable felling compared to other parameters with the least error of 1.94, 18.87, 13.67, 0.91, 7.80, and 0.34 %, respectively. Some of the main advantages of the ANFIS scheme are that it is adaptable to the optimization and adaptive methods, and is computationally efficient.