Solution of metrological water-ecological problems using fuzzy logic methods

This paper presents the efficacy of a “tuned” fuzzy logic method at determining the height of the boundary layer using the measurements from a 1280 MHz lower atmospheric radar wind profiler located in Gadanki (13.5°N, 79°E, 375 mean sea level), India, and discusses the diurnal and seasonal variations of the measured convective boundary layer over this tropical station. The original fuzzy logic (FL) method estimates the height of the atmospheric boundary layer combining the information from the range‐corrected signal‐to‐noise ratio, the Doppler spectral width of the vertical velocity, and the vertical velocity itself, measured by the radar, through a series of thresholds and rules, which did not prove to be optimal for our radar system and geographical location. For this reason the algorithm was tuned to perform better on our data set. Atmospheric boundary layer heights obtained by this tuned FL method, the original FL method, and by a “standard method” (that only uses the information from the range‐corrected signal‐to‐noise ratio) are compared with those obtained from potential temperature profiles measured by collocated Global Positioning System Radio Sonde during years 2011 and 2013. The comparison shows that the tuned FL method is more accurate than the other methods. Maximum convective boundary layer heights are observed between ~14:00 and ~15:00 local time (LT = UTC + 5:30) for clear‐sky days. These daily maxima are found to be lower during winter and postmonsoon seasons and higher during premonsoon and monsoon seasons, due to net surface radiation and convective processes over this region being more intense during premonsoon and monsoon seasons and less intense in winter and postmonsoon seasons.

Bu çalışmada, yapay zekâ yöntemlerinden biri olan bulanık mantık yöntemi kullanılarak, çelik boru profillerin çekme ve basınç kuvveti etkisindeki kapasitelerini belirleyebilmek için iki adet bulanık model oluşturulmuştur. 2018 Türk Çelik yapılar Yönetmeliğinde belirtilen GKT yöntemine göre oluşturulan her iki bulanık modelde de, çelik sınıfı S355 olarak sabit olarak tutulurken, kesit çapı (D), profil et kalınlığı (t) ve eleman uzunluğu (L) değişken parametreler olarak dikkate alınmıştır. Eksenel çekme kapasitesi (Tn) ve eksenel basınç kapasitesi (Pn) ayrı ayrı olarak bu modellerin çıktı parametrelerini oluşturmuşlardır. Her iki modelin oluşturulmasında aynı girdi değişkenleri değerlerine sahip ancak çıktı parametreleri farklı olan 1400 ‘er adet örnek çözüm kullanılmıştır. Kullanılan bu örnek çözümlerin haricinde 988 ‘şer adet farklı örnek çözüm ile bu modeller test edilerek, sırasıyla maksimum % 2.764 ve maksimum % 4.076 hata ile eksenel çekme ve basınç dayanımlarının tahminde kullanılabilecekleri ortaya konulmuştur. Daha sonra geliştirilen bulanık modellere, bulanık ters mantık yöntemi 3 farklı izostatik düzlem kafes sistem örneği için uygulanarak bu kafes sistemleri oluşturan çubuk elemanların tasarımları gerçekleştirildikten sonra dayanım kontrolleri karşılaştırmalı olarak 2018 Türk Çelik yapılar Yönetmeliğinde belirtilen GKT yöntemi ile gerçekleştirilmiştir. Sonuç olarak, bulanık mantık ve bulanık ters mantık yöntemlerinin birlikte aynı sayısal veriyi kullanarak boru kesitli çelik kafes sistem elemanların kapasitelerinin belirlenmesinde ve aynı zamanda tasarımlarının gerçekleştirilmesinde model hataları da dikkate alınarak güvenle kullanılabilecekleri ortaya konulmuştur.

In this study, the four landslide susceptibility (LS) mapping methods, frequency ratio (FR), analytic hierarchy process (AHP), artificial neural networks (ANN) and fuzzy logic (FL) method, are compared. The study has been conducted in Taskent (Konya, Turkey) Basin which is located between 36.88 N to 36.95 N latitudes and 32.35 E to 32.53 E longitudes. The survey area is approximately 80 km2. The FR, AHP, ANN and FL methods are used to map LS. Thematic layers of fourteen landslide conditioning factors including landslide inventory, elevation, slope, slope aspect, plan, and profile curvature, sediment loading factor, stream power, and wetness index, drainage, and fault density, distance to drainage, and fault, geological units, and land use-land cover are used for preparing the LS maps. Estimation power of models has been evaluated by the relative operating characteristic curve method. The areas under the curve for FR, AHP, ANN and FL method have been computed as 0.926, 0.899, 0.916 and 0.842, respectively. These results showed that FR method is relatively good, whereas FL method is a relatively poor estimator for susceptibility. The validity of the LS maps was evaluated by test landslides. The 58 test landslides (76 pixels), 43 training landslides (200 pixels), and 101 total landslides (276 pixels) have been put onto the LS maps prepared by the various methods. The percentages of the existing landslide pixels within the different landslide occurrence potential classes were determined. It is determined that a significant portion of all landslides (76% in the ANN, 83% in the FR, 87% in the AHP and 89% in the FL method) belong to the high and very high LS class. The produced four susceptibility maps were also compared using cross-correlation methods. The cross-correlation coefficients were found to be 0.82, 0.70, 0.63, 0.54, 0.48, and 0.45 for AHP versus FR, FR versus FL, AHP versus FL, AHP versus ANN, FR versus ANN, and FL versus ANN maps, respectively. Here, the confidence level is 0.95. The FR and AHP methods have been assessed to be more suitable methods among other used methods.

The development of the current era, and the rapid development of technology and the need for a significant increase in demand, as well as pollution, the water sector, especially the river has experienced a decline in water quality even to the occurrence of pollution, resulting in water can no longer be consumed either by human body also for other needs. Some of the systems that were developed began to be able to process existing data, be it conditions from water, chemical observations or physically. This is done because water is a necessity that cannot be tolerated, so this research is done to help fulfill or even provide a calm warning of water quality. With the development of Intemet of Things (IoT) the monitoring system will develop, because with the existence of technology such as low-power wide-area network (LPWAN) as specific as possible, short data can be sent using lower power. In this research, it was proven that the author could make a monitoring system and classification of river water pollution. By using an artificial intelligence, using the fuzzy logic method. The results of system testing show that the average accuracy of the monitoring system results is 99.7% and the results of the appropriate classification values are based on the results of system testing.

Comparison of performances of fuzzy logic and adaptive neuro-fuzzy inference system (ANFIS) for estimating employee labor loss

Fuzzy logic and statistical-based modelling of the Marshall Stability of asphalt concrete under varying temperatures and exposure times

Abstract. Lakes are under increasing pressure due to widespread anthropogenic impacts related to rapid development and population growth. Accordingly, many lakes are currently undergoing a systematic decline in water quality. Recent studies have highlighted that global warming and the subsequent changes in water use may further exacerbate eutrophication in lakes. Lake evolution depends strongly on hydrologic balance, and therefore on groundwater connectivity. Groundwater also influences the sensitivity of lacustrine ecosystems to climate and environmental changes, and governs their resilience. Improved characterization of groundwater exchange with lakes is needed today for lake preservation, lake restoration, and sustainable management of lake water quality into the future. In this context, the aim of the present paper is to determine if the future evolution of the climate, the population, and the recharge could modify the geochemistry of lakes (mainly isotopic signature and quality via phosphorous load) and if the isotopic monitoring of lakes could be an efficient tool to highlight the variability of the water budget and quality. Small groundwater-connected lakes were chosen to simulate changes in water balance and water quality expected under future climate change scenarios, namely representative concentration pathways (RCPs) 4.5 and 8.5. Contemporary baseline conditions, including isotope mass balance and geochemical characteristics, were determined through an intensive field-based research program prior to the simulations. Results highlight that future lake geochemistry and isotopic composition trends will depend on four main parameters: location (and therefore climate conditions), lake catchment size (which impacts the intensity of the flux change), lake volume (which impacts the range of variation), and lake G index (i.e., the percentage of groundwater that makes up total lake inflows), the latter being the dominant control on water balance conditions, as revealed by the sensitivity of lake isotopic composition. Based on these model simulations, stable isotopes appear to be especially useful for detecting changes in recharge to lakes with a G index of between 50 and 80 %, but response is non-linear. Simulated monthly trends reveal that evolution of annual lake isotopic composition can be dampened by opposing monthly recharge fluctuations. It is also shown that changes in water quality in groundwater-connected lakes depend significantly on lake location and on the intensity of recharge change.

Subject. Decoding and decision making models, methods and algorithms for elementary signals of receiving devices of distributed control systems elements. Purpose. Development, research and realization of soft decoding and decision making method for elementary signals (channel symbols) within receiving devices of distributed control systems elements based on the fuzzy logic fundamentals and methods. Methodology of research. The analysis of signals distortions by noise of different sources and forms is carried out in this paper. The «quasioptimum» receiving methods for taking account of distortions are analyzed. A condition of uncertainty often occurs at reception so it is difficult to correlate the distorted signal with any of the possible basic (transmitted) signals. The probability of the error at the same time considerably increases. The application of fuzzy sets and fuzzy logic math fundamentals for taking into account and the subsequent removal of uncertainty when decision making is offered. The elementary signals soft decoding (decision making) method based on the fuzzy sets theory and fuzzy logic methods is developed. The decision making device model with Fuzzy Logic Toolbox (MathWorks MatLab) for the offered decoding method application is developed and researched. The common block circuit of the elementary signals quasioptimum receiver is released and the algorithm of it's functioning is described. Research results. The formal description of elementary signals distortions is executed, the variables for decision making are entered. The decision making method of received symbol based fuzzy logic fundamentals is developed; input and output variables and their membership functions are defined; productional rules are formulated; defuzzyfication algorithm is offered. The common block circuit of receiving device is developed used offered decision making method for conclusion formations about received symbol. The simulation and research of the offered circuit is executed; the quantitative assessments of their functioning are received. Application. The offered decision making method based on fuzzy logic fundamentals is planned to be used within elementary signals decision making device. This device is the general node at the common block circuit of receiving device within distributed control systems elements. Conclusions. The researching of the developed receiving device model has shown that the decision making method provides a preset reliability indicators, assumes the computing complexity decreasing due to the arithmetic operations using and the possibility of decision making model parameters adaptation to the change of external conditions (change of error model parameters in a communication channel, increase in requirements to reliability, etc.). It allows to increase the efficiency and reliability of soft decoding applied algorithms.

Clustering is an effective strategy to minimize the energy consumption of nodes in energy-constrained wireless sensor networks. In clustered wireless sensor networks, the network is divided into multiple clusters, and each cluster has a coordinator called cluster head, which collects data from its cluster members and forwards it to the base station through other cluster heads. Cluster wireless sensor networks often have hot spot problems. Due to high energy consumption caused by data forwarding load, cluster heads near the base station die earlier. This kind of node death leads to the coverage loophole of the network early and reduces the life cycle of the network. Unequal clustering is a technology to solve this problem. In non-uniform clustering wireless sensor networks, the size of clusters near the base station is smaller than that far away from the base station. In the process of cluster formation, non-cluster-head nodes are generally added to nearby cluster-head nodes. In this paper, an unequal clustering protocol based on fuzzy logic and entropy weight method (FEUC) is proposed to extend the life cycle of the network. This protocol makes the network form clusters of different sizes. Fuzzy logic method is used to select cluster heads and non-cluster heads join cluster heads to form clusters. The objective entropy weight method is used to select relay cluster heads to implement multi-hop routing strategy. Mamdani method is used for fuzzy reasoning. The proposed protocol is compared with the low-energy adaptive clustering hierarchy (LEACH) protocol, the energy-aware unequal clustering fuzzy protocol (EAUCF), and the fuzzy-based unequal clustering protocol (FUCA), in all scenarios, the proposed protocol has better performance.

The development and distribution of geologically complicated fault structure have the characteristics of uncertainty, randomness, ambiguity, and variability. Therefore, the prediction of complicated fault structures is a typical nonlinear problem. Neither fuzzy logic method nor artificial neural network alone can solve this problem well because the fuzzy method is generally not easy to realize adaptive learning function, and the neural network method is not suitable for describing sedimentary microfacies or geophysical facies. Therefore, taking the marginal subsags in the Jiyang Depression, Eastern China, as a study case, this paper uses the method of combining artificial neural network and fuzzy logic to study geologically complicated fault structure prediction model. This paper expounds on the research status and significance of geologically complicated fault structure prediction model, elaborates the development background, current status, and future challenges of artificial neural networks and fuzzy logic, introduces the method and principle of fuzzy neural network structure and fuzzy logic analysis algorithm, conducts prediction model design and implementation based on fuzzy neural network, proposes the learning algorithm of fuzzy neural network, analyzes the programming realization of fuzzy neural network, constructs complicated fault structure prediction model based on the artificial neural network and fuzzy logic, performs the fuzzy logic system selection of complicated fault structure prediction model, carries out the artificial neural network structure design of complicated fault structure prediction model, compares the prediction effects of the geologically complicated fault structure model based on artificial neural networks and fuzzy logic, and finally discusses the system design and optimization of the prediction model for geologically complicated fault structures. The study results show that the fuzzy neural network fully integrates the advantages of artificial neural network and fuzzy logic system; based on the clear physical background of fuzzy logic system, it effectively integrates powerful knowledge expression ability and fuzzy reasoning ability into the network knowledge structure of neural network, which greatly improves the prediction accuracy of geologically complicated fault structure.

Comparison between fuzzy logic and water quality index methods: A case of water quality assessment in Ikare community, Southwestern Nigeria

In this study, a fuzzy logic model was constituted by using the Fuzzy Logic (FL) method, which is one of the traditional artificial intelligence (AI) methods, in order to estimate the shear strength of reinforced concrete (RC) beams with limited ductility. In this model, beam width(bw), beam height(h), characteristic concrete compressive strength(fck), transverse reinforcement diameter(T), the number of arms bearing the shear force of the transverse reinforcement(n) and transverse reinforcement spacing(s) were taken into account as variable parameters. The model developed by using the problem data containing the solutions of shear force strength of 2640 beams with different cross-section properties were tested with 480 beam solutions different from these data. In the tests of the developed FL model, maximum percentage error, minimum percentage error, average percentage error and correlation coefficient values were obtained as 3.604, -0.091, 1.514 and R2=0.999678. By applying the fuzzy inverse logic method (FIL), which was recently developed by the author of this study, on the FL model, which is seen to have been developed quite sensitively from the test results, a total of 521 designs were obtained for 15 different RC beams with limited ductility subjected to shear. In order to check the accuracy of these designs, after shear strengths were obtained by conventional computations for these designs, % error and correlation coefficients were computed between the obtained strength values and the shear force values taken into account for the design. The promising results show that the FIL method can be used in the design of RC beams under shear force and even in other scientific studies such as design, optimization and control.

Many studies have examined earthquake’s impacts on hydrological changes such as drying up and flooding of (water) wells, fluctuation of groundwater levels, and changes in water quality. This paper aims to present water quality changes in the aftermath of a November 2010 earthquake in Kraljevo. Water quality changes followed hydrological, geological, and geomorphological changes. The water parameter concentrations were measured before the earthquake in 2010 and after that in 2010 and 2011, as well as 2009 and 2012. The data from two hydrological stations were used: Kraljevo Zapadna Morava and Kraljevo Ibar. The Canadian Water Quality Index was applied for the calculation of water quality. This method defines the overall water quality and the specific quality of water used for drinking, aquatic habitats, recreation, irrigation, and livestock. A significant decline in the quality of water used for aquatic habitat and a less significant one in the overall quality and the quality of water used for irrigation was recorded in the hydrological station Zapadna Morava. Increased heavy metal concentrations were detected, which caused water quality impairment. A minor decline in the overall water quality and the quality of water used for aquatic habitats was recorded in the hydrological station Kraljevo Ibar.

This research addresses the issue of resource and power allocation in small cell networks, and focuses on two aspects: i) the interference coordination among cells; and ii) the resource allocation among the users served by the same cell. Due to the density of small cells, centralised interference coordination schemes require an enormous level of communication among cells. Fuzzy logic (FL) is a promising low-complexity approach to realise autonomous interference coordination that does not need communication between cells. In this paper, we propose a novel FL method and associated decision-making algorithm for tackling resource allocation in small cell networks. Unlike the traditional FL method using the values of two states ‘yes’ and ‘no’ to describe how much a resource block (RB) should or should not be allocated, the proposed method employs a 3-state criterion that distinguishes high-quality RBs from medium-quality RBs. Also, the issue of allocating the RBs of a single cell to multiple users is studied in the FL method. Simulation results show that the proposed method can notably improve the performance of the traditional FL method in terms of both throughput and user satisfaction, without requiring extra processing power.

Among the set of parameters for which data are collected for decision-making based on artificial intelligence methods, often only some of the parameters are significant. This article compares methods for determining the significant parameters based on the theory of mathematical statistics, and fuzzy and boolean logic. The testing was conducted on several test data sets with a different number of parameters and different variability of parameter values. It was shown that for data sets with a small number of parameters (<5), the most accurate result was given for a method based on the theory of mathematical statistics and boolean logic. For a data set with a large number of parameters—the most suitable is the method of fuzzy logic.