Search

Time series classification is an increasingly attractive field with the appearance of new problems in an expanding digitalized world. Most of the proposals in the state-of-the-art have focused just on improving the results' performance, leaving interpretability on a secondary level. The available interpretable proposals do not provide competitive results, which is an issue to be addressed. This paper introduces a new fuzzy feature-based time series classification method, which joins the ability of time series features to capture essential information about the time series with Fuzzy logic. This proposal allows the fuzzy-based approach to incorporate global information about the behavior of time series in the membership calculation with the aim of improving the performance and interpretability of the results by using an interpretable classifier. The proposed method has been evaluated over the 112 state-of-the-art time series classification datasets from the UCR repository, and the results obtained show a better performance. Furthermore, the combination of time series features and fuzzy memberships has also increased the interpretability of final models. • PLAYTIME incorporates temporal information into fuzzy environments. • PLAYTIME combines fuzzy- and time-features to improve time series classification. • PLAYTIME improves interpretability and performance by using a tree-based classifier. • PLAYTIME is tested with 112 datasets of the UCR repository. [ABSTRACT FROM AUTHOR]

In actual distributed parameter systems (DPSs), each spatial point has nonlinear energy transfer with its local neighbor points. Also, this energy transfer is affected by the past states. However, these properties are often ignored by most of modeling methods, which causes these methods ineffective in modeling of DPSs. Aiming for this problem, a spatiotemporal kernel-local-embedding (STKLLE) Modeling approach is proposed here to reconstruct the nonlinear spatiotemporal dynamics of DPSs. First, in order to present the complex dynamics on space, a STKLLE strategy is developed to extract space basis functions (SBFs). On the one hand, this STKLLE method represents the energy transfer relation with its neighboring points and maintains this local relation in model. On the other hand, it considers the influence of the adjacent past states to the current state. Then, using T–S fuzzy algorithm, a temporal model is designed to represent the temporal dynamics of DPSs in each sampling period. Integrating these SBFs and the temporal fuzzy model, a spatiotemporal model is constructed to well present and predict the nonlinear spatiotemporal dynamics in DPSs. Through the actual experiment on Lithium-ion batteries and heating oven, the effectiveness of this proposed model is detailly verified, and quantitative comparisons with several data-driven modeling algorithms are further carried out to demonstrate the model efficiency. • A spatiotemporal KLLE method is designed to extract nonlinear relations of the local neighbor points and adjacent states. • A T-S fuzzy temporal model is developed to construct the temporal dynamics of DPSs. • A spatiotemporal model is developed to reconstruct the spatiotemporal dynamics of DPSs. • This proposed method is verified by theoretical analysis and experimental studies. [ABSTRACT FROM AUTHOR]

The article is devoted to the problem of underutilization of the country's labor potential in the face of women with young children. The relevance of research in the field of support for families with young children and the development of additional measures to support them is further explained. The authors propose to use a mathematical model based on soft computing for predictive estimation of the number of women with children from 0 to 3 years old, who are ready to go to work, taking into account the age of the child. The calculation of numerical indicators is based on the prediction of the Federal Statistics Service of the Russian Federation for the estimated population of the Russian Federation in the context of ages up to 2035. [ABSTRACT FROM AUTHOR]

This paper considers the problem of fuzzy overhead crane system modelling and finite-time stability/boundedness via sliding mode control (SMC) method. Due to the strong coupling of control input, the fuzzy technique is utilized to linearize the overhead crane system and a fuzzy overhead crane model is established with appropriate membership functions. Considering the bad effect, including the swing of hook and plates, the external disturbances of the friction and air resistances, is inevitable during the transportation of copper electrode plates, the SMC method is adopted to stabilize the fuzzy system and robust to these interference signals. Furthermore, taking the time cost of actual industry into account, the finite-time stability/boundedness is introduced to achieve the state of system could be stable in a specified finite time. Moreover, the reaching law of sliding mode dynamics is analysed and the sufficient conditions for finite-time stability/boundedness of system state are formulated, respectively. Finally, the simulation results of the control strategy put forward in this article with the comparisons on some existing algorithms are provided to verify the effectiveness of the control strategy in the copper electrolytic overhead crane system. • The fuzzy model is constructed via piecewise linearization with appropriate rules. • The integral-type sliding surface is to avoid the derivative of membership function. • The finite-time stability/boundedness is adopted to guarantee the system to be finite-time stable. [ABSTRACT FROM AUTHOR]

In this study, fuzzy modeling and service control based on optimal N -policy for fault tolerance system have been investigated. The impacts of failures and recovery along with the reboot process are taken into account for the assessment of performance indices of the system operating under redundancy and provision of maintainability. The non-Markovian M / G / 1 model of the fault-tolerant system with vacationing server is developed by using the supplementary variable to represent the remaining time to repair and further employing recursive approach. The parametric non-linear programming is used to derive fuzzy performance metrics. The sensitiveness of parameters concerning system indices is done. The cost function is framed to obtain the optimal descriptors and minimal cost using harmony search. • Developed model provides valuable insights to fulfill the fault tolerance objective. • The failure and repair rates are fuzzified using trapezoidal fuzzy numbers. • The system size distributions are examined in crisp as well as in fuzzy environments. • Soft computing approach based on harmony search method is used for optimization. • A real-life example of Assembly Line Monitoring System is illustrated in this article. [ABSTRACT FROM AUTHOR]

This paper makes a direct contribution to the mathematical theory and practical implementation of interpretable deep fuzzy learning whilst addressing the model interpretability challenge posed by the typical non-interpretable nature of training data. A deep autoencoder, composed of a finite number of stochastic fuzzy filters, is learned using variational Bayes for an efficient representation of high-dimensional feature vectors at different levels of abstraction. The robustness of the deep model towards data outliers is achieved by incorporating heavy-tailed distributed noises in the inference mechanism. The proposed deep stochastic fuzzy autoencoder makes it possible to have an interpretable classification by means of an induced mapping from a non-interpretable feature space to an interpretable parameter space. The mapping induced by our autoencoder can be used to explain the classifier's predictions by interpreting the non-interpretable high-dimensional feature vectors. The experimental results obtained on various benchmark datasets (e.g., Freiburg Groceries, Caltech-101, Caltech-256, Adobe Panoramas, and MNIST) show that our proposed approach not only outperforms widely used machine learning methods in classification tasks but brings the added value of interpretability as a further advantage. [ABSTRACT FROM AUTHOR]

• Compact UAV leveraging Coandă effect for exceptional maneuverability. • Exploring theoretical study, mechatronic design, and manufacturing complexities of Coandă UAV. • First application of Fuzzy Logic Controller to Coandă-effect UAV, surpassing PID control. • Advantageous Sugeno model provides faster, more robust control in uncertain environments. • Systematic comparison shows FLC strategy outperforms PID approach by 35.23% in settling time. • Comprehensive experimentation in Matlab® and Simulink for microcontroller-based UAV. • Groundbreaking fusion of novel design and advanced control techniques for Coandă UAVs. • Addressing unique aerodynamic challenges, contributing significantly to UAV research. Recent years have experienced a notable surge in unmanned aerial vehicles (UAV) research, prompting exploration into innovative concepts. This paper introduces a compact UAV harnessing the Coandă effect, an underexplored phenomenon in fluid mechanics. Featuring a single lift motor and two types of flaps, this UAV offers exceptional maneuverability, presenting significant challenges compared to conventional multi-rotor UAVs. To address these challenges, we explore the theoretical study, mechatronic design, and manufacturing complexities of the Coandă UAV. Emphasizing the distinctiveness of our work, we assess a Fuzzy Logic Controller (FLC) for UAV stabilization, marking the first application of such techniques to a Coandă-effect UAV, in contrast to the Proportional-Integral-Derivative (PID) control employed by other researchers. This innovative application of Fuzzy logic, particularly the Sugeno model, proves advantageous, offering faster and more robust control in uncertain or noisy environments. The proposed FLC strategy is systematically compared against a classical PID control approach, formulated based on the Mamdani and Sugeno models, optimized and manually tuned using a genetic algorithm. Our results showcase a significantly improved settling time of 0.417 s with the FLC strategy, surpassing the PID control approach by 35.23%. To substantiate our findings, we present comprehensive experimentation conducted at both software and hardware levels using Matlab® and Simulink for a microcontroller-based UAV. This groundbreaking fusion of novel design and advanced control techniques not only addresses the unique challenges posed by the Coandă UAV's aerodynamics but also contributes significantly to the field of UAV research. [ABSTRACT FROM AUTHOR]

This study proposes a novel methodology for the extraction of a hierarchical Takagi-Sugeno fuzzy rule-based architecture from data. This architecture reduces the number and complexity of involved fuzzy rules, and, in many cases, improves the predictive performance of the model. The proposed hierarchical architecture takes the form of a cascading topology in which the predicted result computed at the previous layer is considered in the output part of the fuzzy rules. We propose a well-defined general methodology for the extraction of this hierarchical topology from data and discuss strategies for feature selection and choosing the number of rules at each level. The performance of the proposed methodology is demonstrated through extensive experiments, including case studies outlining specific behaviors and parameterizations, and comparative experiments showing the performance of the proposed architecture compared to a standard flat fuzzy rule-based system. [ABSTRACT FROM AUTHOR]

• Utilization of fuzzy based model to predict methane generation from landfills. • Calibration of the model based on data from 20 landfills in Ontario, Canada. • Validation of the model using data from 10 big landfills in Ontario, Canada. • Comparison of fuzzy based mode with first order models for LFG generation. In this study, multi-criteria assessment technique is used to predict the methane generation from large municipal solid waste landfills in Ontario, Canada. Although a number of properties determine the gas generation from landfills, these parameters are linked with empirical relationships making it difficult to generate precise information concerning gas production. Moreover, available landfill data involve sources of uncertainty and are mostly insufficient. To fully characterize the chemistry of reaction and predict gas generation volumes from landfills, a fuzzy-based model is proposed having seven input parameters. Parameters were identified in a linguistic form and linked by 19 IF-THEN statements. When compared to measured values, results of the fuzzy based model showed good prediction of landfill gas generation rates. Also, when compared to other first order decay and second order decay models like LandGEM, the fuzzy based model showed better results. When plotting the LandGEM and Fuzzy model values to the actual measured data, the fuzzy model resulted in a better fit to actual data than the LandGEM model with a coefficient of determination R2 of 0.951 for fuzzy model versus 0.804 for LandGEM model. The results show how multi-criteria assessment technique can be used in modelling of complicated processes that take place within the landfills and somehow accurately predicting the landfill gas generation rate under different operating conditions. [ABSTRACT FROM AUTHOR]

Adaptive neuro-fuzzy inference system (ANFIS) is a well-known neuro-fuzzy model for approximating highly complex non-linear systems. ANFIS uses precise fuzzy modelling concept that aims at accuracy of a fuzzy model being designed than on interpretability. But interpretability of a fuzzy system is an equally important aspect of fuzzy modelling as accuracy. So far the research based on ANFIS has been mostly application based due to which the various issues related to the interpretability of ANFIS have not been dealt with. The rule base of ANFIS is typically obtained using data driven clustering algorithms. But this process introduces redundancy in the system in terms of similar fuzzy sets and redundant fuzzy rules which unnecessarily increases system complexity. This in turn reduces both the interpretability as well as generalization capability of ANFIS. Additionally in case of ANFIS, unconstrained gradient descent based learning algorithms are used to fine-tune the membership function parameters which usually result in a rule base with inconsistent, excessively overlapping and indistinguishable membership functions for input variables and thus the interpretability of the final optimized system is not guaranteed. This paper is based on addressing the issue of rule base redundancy in ANFIS to reduce complexity and enforcing constraints during learning phase to ensure interpretability of the final optimized system. Rule base redundancy is removed using similarity analysis based rule base simplification in which similar fuzzy sets are merged and subsequently resulting fuzzy rules with equal premises are combined. Hybrid learning technique which is an efficient parameter tuning method for ANFIS is constrained to prevent inconsistency, excessive overlapping and inclusion of membership functions so that the final fuzzy partitions of inputs stay interpretable. The empirical analysis of the impact of rule base simplification and constrained learning on ANFIS is done by application to two well-known benchmark problems and a real world stock price prediction problem. The introduction of rule base simplification and constrained learning in ANFIS modeling has shown better results in terms of obtaining a desired accuracy-interpretability tradeoff than conventional ANFIS. [ABSTRACT FROM AUTHOR]

The ascent prediction of high-altitude zero-pressure stratospheric balloons is an important aspect of targeted test flight. Prediction of the balloon ascent rate is the prerequisite for many of the flights as it helps in planning ballasting and valving manoeuvres. In this paper, a standard analytical model, a fuzzy model and a statistical regression model are developed and compared to predict the zero-pressure balloon ascent. The flight data is extracted from the Esrange balloon service system for zero-pressure balloons with different payload capability, and several potential explanatory variables are computed for every sampled climbed segment. For the fuzzy modelling approach, a fuzzy c-mean clustering algorithm is used for system identification and prediction. For the regression approach, a Gaussian process regression is used, and principal component analysis is applied for finding the significant inputs. The result shows that the data driven approaches are more efficient than the standard analytical model. [ABSTRACT FROM AUTHOR]

The identification of DNA N4-methylcytosine (4mC) sites is an important field of bioinformatics. Statistical learning methods and deep learning have been applied in this direction. The previous methods focused on feature representation and feature selection, and did not take into account the deviation of noise samples for recognition. Moreover, these models were not established from the perspective of prediction error distribution. To solve the problem of complex error distribution, we propose a maximum multi-correntropy criterion based kernelized higher-order fuzzy inference system (MMC-KHFIS), which is constructed with multi-correntropy fusion. There are 6 4mC and 8 UCI data sets are employed to evaluate our model. The MMC-KHFIS achieves better performance in the experiment. • For complex error distribution, multi-correntropy based fuzzy system is built. • Fuzzy kernel is built to solve feature space projection in each fuzzy subset. • An efficient iterative algorithm is employed to optimize the fuzzy system. [ABSTRACT FROM AUTHOR]

Supply chain management is a multidisciplinary engineering problem. In this paper, a polymorphic uncertain equilibrium model (PUEM) is constructed to capture the joint maximization of the profits for the manufacturers and retailers in a supply chain network. To ensure applicability of the model in practice, the demand of the consumers is regarded as a continuous random variable, the holding cost of the retailer and the transaction cost between the manufacturer and retailer are described by fuzzy sets. For the PUEM, a deterministic equivalent formulation (DEF) is first derived by compromise programming approach such that the existing powerful algorithms in the standard smooth optimization are employed to find an approximate equilibrium point for the uncertain problem. Actually, the DEF turns out to be a nonlinear complementarity problem (NCP), a special variational inequality. Thus, a modified partially Jacobian smoothing algorithm is developed to solve the corresponding NCP, where the gradient information of the model is used to efficiently generate search direction. Sensitivity analysis offers a number of useful managerial implications based on practical applications of the model. [ABSTRACT FROM AUTHOR]

Prediction of the contact angles and sliding angles of liquid drops is so difficult, because the interaction among the variables, which have impact on the angles, is so complex. Therefore, in this paper fuzzy logic was used to develop prediction models. Experimental sliding angle and contact angles of liquid drops on the metal samples with several surface treatments were divided into training data and testing data. By using the knowledge, which was extracted from the training data and experience of authors, the effective if-then rules were developed. Then, the weight of the rules was optimized by particle swarm optimization. The obtained results for testing data by using proposed Fuzzy_CA and Fuzzy_SA models showed that the regression index for the contact angles and sliding angles were 0.9970 and 0.9980, respectively. It means that the predicted angles are so close to measured angles and the proposed fuzzy based models are so reliable. [ABSTRACT FROM AUTHOR]

In this paper, a robust fuzzy modeling method is proposed for strongly nonlinear systems in the presence of noise and/or outliers. The proposed method integrates the advantages of the fuzzy structure, the manifold learning, and the weighted least squares support vector machine (LS-SVM). First, the Gustafson–Kessel clustering algorithm (GKCA) is applied to split the training data set into several subsets to determine the fuzzy rules and premise parameters. Then, a new objective function is constructed based on the fuzzy structure, the weighted LS-SVM, and the manifold regularization, which takes into account robustness and the intrinsic geometry of the data. A solving method is further developed, from which the fuzzy model is achieved and can effectively approximate a nonlinear system with various types of random noise. The proposed method is applied to an artificial case as well as a practical hydraulic actuator, demonstrating its effectiveness in modeling of a nonlinear system even under noise. [ABSTRACT FROM AUTHOR]

Many industrial processes belong to distributed parameter systems (DPSs) with unknown spatiotemporal dynamics and complex boundary conditions. However, attentions to both temporal and spatial dynamics in the control law are less paid in the existing control methods, which often makes them challenging to achieve accurate control. Here, a spatiotemporal fuzzy control approach with consideration of both temporal and spatial dynamics is proposed for unknown and complex DPSs. First, a spatiotemporal fuzzy model is developed to reconstruct dynamics of nonlinear DPS. Since it constructs a two-layer fuzzy rules (i.e., temporal fuzzy rule and spatial fuzzy rule) to consider both the nonlinear dynamics on time and the nonlinear energy transfer on space, it can effectively achieve the model of DPSs. On this basis, a spatiotemporal fuzzy controller is developed according to the developed two-layer fuzzy rules, which means that this derived control law considers both temporal and spatial dynamics. Then, a two-step solution method is designed for the spatiotemporal control law. Stability conditions of the control system are rigorously deduced by transforming the solving process to a series of linear matrix inequalities (LMIs). The stability and effect of the proposed spatiotemporal control strategy are demonstrated by mathematical proof and case studies. Comparison results demonstrate that the proposed method has better control performance (relative errors and mean absolute percentage errors are bounded in 4%). • A spatiotemporal fuzzy control approach is proposed for unknown and complex DPSs. • A two-layer fuzzy rule is designed to consider the nonlinear dynamics on both time and space. • A two-step solving method is developed to derive the spatiotemporal control law. • Theoretical analysis and experiments show the effectiveness of this control method. [ABSTRACT FROM AUTHOR]

In this study, a quantitative and comprehensive evaluation of environ-economic benefits of anaerobic digestion (AD) of food waste was conducted on an operational project in China. Fuzzy evaluation method based on life cycle assessment and cost-benefit analysis was employed. Single-factor evaluation of environmental impacts and energy consumption indicated that AD was a green and clean energy producing technology. The study indicated that the total environmental impact was not significant at 6.65 E-03, and the net energy output (186.01 MJ) was slightly higher than the net energy input (167.47 MJ), when only methane production was considered. However, economic benefits were not ideal, recording loss of 64.99 RMB for each ton of food waste. Additionally, results of comprehensive evaluation conducted using fuzzy mathematical model were consistent with above results. Environmental benefits, energy consumption, and economic benefits of AD technology were 4.75, 3.58, and 1.36, corresponding to grades I, Ⅱ, and IV, respectively. Single benefits decreased in the order of environmental impact > energy consumption > economic benefit, indicating that economic benefit is the restrictive factor in integrated environ-economic benefits of AD technology in practice. Thus, increasing economic benefit should be the focus of research and management processes. Additionally, overall environ-economic benefit of AD rated good (Grade II), with a value of 3.39. Further sensitivity analysis results confirmed the stability of the comprehensive evaluation model. The established fuzzy mathematical evaluation model can realize comprehensive and quantitative evaluation of environ-economic benefits of AD technology; serve as valuable reference for perfecting evaluation systems, and assist in rational choice of renewable energy recovery technology from food waste. [ABSTRACT FROM AUTHOR]

Nano-ZnO enters landfills mostly through disposal of cosmetics, sunscreens and catalysts. However, its effects on waste degradation are still unclear. In this paper, a fuzzy-based model is proposed to predict biogas and methane production from simulated bioreactor landfill with and without ZnO nanomaterials. Eight deterministic inputs (pH, RedOx potential, chemical oxygen demand, volatile fatty acids, alkalinity, Zn concentration, Zn background and leachate recirculation flow rate) were identified as antecedent variables. Two outputs, or consequents, were chosen: biogas production rate and methane fraction. Antecedents and consequents were linked by 66 IF-THEN rules, which stated the effects of the input parameters in a linguistic form. The fuzzy model was tested on the data of a lab-scale study simulating a bioreactor landfill with 100 mg of added nano-ZnO per kg of dry waste. Experimental results indicated that the addition of nano-ZnO resulted in a reduction of methane generation by about 30%.The fuzzy model showed good performance in the prediction of methane generation; in addition, the comparison with the commonly used Gompertz equation showed that the fuzzy model is more consistent with the data. Fuzzy modelling could easily handle the Zn concentration together with other parameters and it highlighted the importance of including this input in the model. The modelling results confirmed the high potential of fuzzy macro-approach in the modelling of very complex processes taking place in landfill environments under different operating conditions. [ABSTRACT FROM AUTHOR]

Two advanced models for forecasting the output power of photovoltaic plants are discussed in details: a black-box Takagi-Sugeno fuzzy model and a physically inspired, semiparametric statistical model (Generalized Additive Model, GAM) based on smoothing splines. The structure of the two models, their strengths and weaknesses, are presented. The models performance is thoroughly compared with the performance of a simple linear model tested under the frame of the European Cooperation in Science and Technology (COST) Action “Weather Intelligence for Renewable Energies”, as a benchmark used also in the forecasting exercise reported in Sperati et al. Energies 8 (2015) 9594. The models are used to forecasting the output power at time horizons of 1–72 h ahead. The data used during the COST competition are used here as input. The present study extends beyond the traditional evaluation of overall model accuracy. Detailed influences of seasonal effects, sun elevation angle and solar irradiance level upon the models performance are assessed. While the accuracy of the simple linear model is not entirely bad, it differs in important details from the two advanced forecasting models. The results show that a moderate, carefully chosen increase in model structure complexity can improve the predictive performance. Suitable penalty on model complexity can help both to enforce parsimony and improve practical forecasting abilities, to a certain extent. The physically inspired GAM comes out as the best performing model. [ABSTRACT FROM AUTHOR]

The water quality (WQ) status of water bodies is highly uncertain and subjective in nature. The present paper addresses a "Fuzzy River Health Index" (FRHI) which is capable of dealing with subjectivities and uncertainties concerning river health at various sites of the Chambal River, India. By considering the parameters like temperature, total solids (TS), pH, dissolved oxygen (DO), biological oxygen demand (BOD), total coliform (TC), phosphate (P) and nitrate (N), the fuzzy model is established. The model uses triangular membership functions for fuzzification and centroid method for defuzzi - fication. The proposed proficient method includes a fuzzy model which include IF-THEN ideas that help to determine River health using WQ parameters. The comparative performance models used are Carlson' s trophic index (C-TSI), and Ecological health index (EHI). This study reveals that FRHI provides fairly good results; therefore, it concludes that the health of Chambal River is within excellent range (FRHI > 80). However, there is an urgent need to develop an effective and sustainable WQ monitoring for this study site, this proposed FRHI provides the flexibility for decision making in an integrated WQ management policies. [ABSTRACT FROM AUTHOR]

In IoT-based WSN applications, energy is a vital parameter since limited residual energy of a node often leads to packet loss, diminished network lifetime, and end-to-end delay. IoT nodes are often resource-constrained, with limited computational and storage capabilities, communication range, and energy-saving potential. To offer an improved Quality of Service (QoS) guarantee, the network lifetime and energy consumption of the WSN-based IoT applications need to be improved. QoS is an important parameter in time-sensitive IoT applications. Hence this paper introduces a novel QoS improvement framework for the WSN-IoT networks, and the objective of this work is twofold. In the first phase, we utilize an Aquila optimizer (AO) for an efficient and reliable cluster head selection which is based on different factors such as node level, distance to the sink node, energy level, etc. The AO algorithm enhances the lifetime of the WSN network by electing the QoS-aware relay node as the cluster head. In the next phase, the Hybrid Fuzzy Levy Flight Particle swarm optimization algorithm (HFLPSO) is presented to enhance the QoS of the network even further by identifying a set of optimal paths to route the packets and measure the reliability of each path via different metrics (packet loss rate, residual energy, end-to-end delay, link stability, and the number of hops). The simulation experiments were conducted using different metrics such as End to End delay, Packet loss rate, and Packet delivery ratio to prove that the proposed model is capable of improving the QoS of the WSN-IoT networks when compared to the different state-of-art methodologies. When compared to the existing techniques, the proposed model offers a 10% improvement in the packet loss rate and a 17% improvement in the packet delivery rate. [ABSTRACT FROM AUTHOR]

The paper focuses on less conservative design of observer-based output feedback control synthesis of discrete-time Takagi–Sugeno fuzzy systems on account of an improved homogenous polynomial approach. Compared with those previous methods in the cited literature, a novel fuzzy observer-based output feedback law is constructed in virtue of utilizing one promising solution to homogenous polynomials that are parameter-dependent on both the current-time and those multi-steps past-time normalized fuzzy weighting functions with a pair of prescribed degrees. It is rather remarkable that more information contained in the normalized fuzzy weighting functions is integrated to build the proposed control law, and thus the conservatism left behind previous results can be released in this work. Moreover, a robust version of the underlying result is also proposed. Finally, the effectiveness of the given approach is demonstrated via some illustrative experiments. [ABSTRACT FROM AUTHOR]

This paper uses climatic measures from a greenhouse to get a fuzzy model of the internal temperature, with the fuzzy model obtained; two control actions are used to control the internal temperature. The fuzzy control is developed by using the inverted fuzzy model. Due the number of climatic variables and to the condition of having a monotonic fuzzy model, there were used two membership functions for the fuzzy partition of each variable. It was used a fuzzy singleton model which is tuned by using batch least squares and updated with recursive least squares. The control actuators are: a proportional servo-valve for the heating, it works at nights when frozen can occur, and the ventilation, it is used during the day to avoid high temperatures, these signals are excluding mutually because the humidity or hot air can be lost generating an extra cost. The greenhouse is used for tomatoes cultivation. [ABSTRACT FROM AUTHOR]

In this study, we explore the combination of two well defined topics in fuzzy systems research: fuzzy rule based systems, and information granulation. Rule based systems are a powerful and well-studied form of knowledge representation, due to their approximation abilities and interpretability. In recent years, these types of systems have become increasingly powerful with regards to modeling accuracy; however, many of these improvements come at the cost of model interpretability. This recent direction of research has left an unexplored avenue towards the generation of increasingly interpretable fuzzy rule based models, which we intend to explore. Information granulation is a relatively new, yet very promising area of research in human centric systems. As a form of knowledge representation, information granulation is very well suited to fuzzy rule based systems, where rules represent linguistic quantities in a, intuitively understandable format. It is notable that the combination of these two concepts has been left largely unstudied. We aim to explore this union by defining a methodology for the construction of a partially granular fuzzy rule based model. The aim of this novel model format is to provide a first step in the improvement of fuzzy model interpretability, through the use of information granulation. We are additionally interested in studying new ways of generating fuzzy rules; hence, we will also look at the use of hierarchical clustering as a potential alternative to the tried and tested Fuzzy C Means clustering algorithm. The models created using hierarchical clustering are then compared with those generated using Fuzzy C Means to evaluate the effectiveness of this algorithm. As a result of these experiments, we demonstrate that partially granular fuzzy rules are capable of providing a significant improvement to fuzzy rule interpretability, and we believe that granular fuzzy models present an exciting avenue of future research in human centric systems. [ABSTRACT FROM AUTHOR]

Conventional portfolio optimization models assume that future of the Stock Market will be predicted by past data. However, regardless of whether how accurate is the past data, this theorem in financial market is not applicable due to the high volatility of the market environment. This research is about optimization problem of fuzzy set that shows the assets return by fuzzy data. Part of the data of the actual financial information, are information from the actual data of Years 2012 and 2013 that have been obtained as fragile (and final) and another part of the survey experts as predictive information was obtained for the years 2014 to 2017 in the form of triangular fuzzy numbers. To optimize portfolio, nonlinear mathematical models for some were specified and presented then using the change of variables technique that in operations research literature is a simple technique, two models could merged and integer linear model variables were created and the results were used to calculate the software Lingo. Finally the results were obtained in accordance with a basics idea of financial economics that whatever the degree of investment risk, is more he want to get more return. [ABSTRACT FROM AUTHOR]

Economic optimal control has been a major concern in modern power plant. The HMPC (hierarchical model predictive control) incorporates both the plant-wide economic process optimization and regulatory process control into a hierarchical control structure, in which the model predictive control technology has been an effective tool for solving the higher-layer economic optimization problems. Since the power plants are typically nonlinear multivariable large-scale processes, applications of the HMPC can be computationally extensive and resulting in nonlinear and non-convex optimization problems. Since the power plant dynamics changes with load, fuzzy model representing the local input–output relations of the nonlinear power plant system is incorporated to facilitate the convex QP (quadratic program) routine, and thus realize the HMPC. Detailed analysis on power plant steam-boiler generation system has been made to demonstrate the effectiveness of the proposed nonlinear HMPC. [ABSTRACT FROM AUTHOR]

The objective of this study was to improve the use of a fuzzy model to supplement rainfall data when the watershed's meteorological station is either far away or suffers a loss of rainfall data. The fuzzy model can also supplement rainfall data when the station is nearby. The accuracy of rainfall data in the EPA's (Environmental Protection Agency) BASINS (Better Assessment Science Integrating Point and Nonpoint Sources) decision support tool is affected by the sparse meteorological data contained in BASINS. This study also assessed the improvement in stream flow prediction with the Hydrological Simulation Program-FORTRAN (HSPF) model contained within BASINS, using the hourly precipitation estimates for the Feitsui reservoir watershed. This study demonstrates that using a fuzzy model to supplement rainfall data has the potential to improve stream flow predictions, thus aiding water quality assessment in the nonpoint water quality assessment decision tool. [ABSTRACT FROM AUTHOR]

In this paper, an efficient genetic algorithm (GA) to generate a simple and well defined TSK model is proposed. The approach is derived from the use of the improved Strength Pareto Evolutionary Algorithm (SPEA-2), where the genes of the chromosome are arranged into control genes and parameter genes. These genes are in a hierarchical form so that the control genes can manipulate the parameter genes in a more effective manner. In our approach, we first apply the back-propagation algorithm to optimize the parameters of the model (parameters of membership functions and fuzzy rules), then we apply the SPEA-2 to optimize the number of fuzzy rules, the number of parameters and to fine tune these parameters. Two well-known dynamic benchmarks are used to evaluate the performance of the proposed algorithm. Simulation results show that our modeling approach outperforms some methods proposed in previous work. [ABSTRACT FROM AUTHOR]

The knowledge of the service life and durability of building components is paramount to sustainable analysis and decision making since it allows a more rational management of the maintenance of building and provides data for life cycle analysis procedures. Nevertheless, predicting the service life of a building or its components is a complex process with which a number of variables are associated. The main difficulties associated with service life prediction are related to the complexity of the degradation phenomena and to the lack of understanding of degradation factors and mechanisms. This paper aims at establishing a model for the service life prediction of rendered facades using a Takagi–Sugeno fuzzy model. The models proposed include the variables that influence the degradation of rendered facades (render age, render type, building height, facade orientation, exposure to damp, and facade protection level). In this study, the degradation condition of 100 case studies located in Portugal is analyzed based only on in situ visual inspections. The proposed models are able to describe appropriately the degradation of rendered facades and to predict the service life of the sample analyzed. [ABSTRACT FROM AUTHOR]

One of the main characteristics of the soil structure, which affects the plant growth and its yield, is its aggregates size. Correct tillage operations leads to prevention from soil degradation and help to maintain and improve its physical, chemical, and biological characteristics. In this paper, a model based on fuzzy logic approach was used to describe the soil fragmentation for seedbed preparation in the composition of primary and secondary tillage implements of subsoiler, moldboard plow and disk harrow as conventional tillage composition in the region. Field experiments were carried out at educational and research farms of faculty of agriculture, University of Mohaghegh Ardabili. In this paper, an intelligent model, based on Mamdani approach fuzzy modeling principles, was developed to predict soil fragmentation during tillage operation. The model inputs included soil moisture content, tractor forward speed and soil sampling depth. The fuzzy model consisted of 50 rules, in which three parameters of root mean square error (RMSE), relative error ( ɛ ), and coefficient of determination ( R 2 ) were used to evaluate the fuzzy model. These parameters were calculated 0.167%, 3.95%, and 0.988%, respectively. According to the results of this research, the fuzzy model can be introduced as one of the methods for predicting soil fragmentation during the tillage operation with high accuracy. [ABSTRACT FROM AUTHOR]

[Display omitted] Rare earth elements (REEs) are considered critical metals globally. About 62% of the global resources of REEs occur associated with carbonatites and alkaline complexes. However, the entire production of REEs in India currently comes from monazite-bearing beach sands, although a variety of REE enriched source rocks, particularly carbonatites and alkaline complexes occur in different parts of the country. There is, therefore, a significant potential in the county for new REE deposit discoveries associated with carbonatites and alkaline complexes. This paper describes a generalised carbonatite-alkaline complex related REE mineral systems model and applies a knowledge-driven model to demarcate REE exploration targets in the Karbi-Meghalaya plateau, NE India. The main components of the mineral systems are (1) pockets of metasomatised subcontinental lithospheric mantle (SCLM) which form fertile source regions for REE-bearing fluids; (2) extensional geodynamics; (3) permeable lithosphere architecture for tapping REE-enriched fluids from SCLM and focusing them to near-surface levels, and (4) a post-emplacement tectonic regime that preserves the deposits. Spatial proxies representing each of these components are mapped and integrated using fuzzy inference system (FIS) to identify prospective targets. Systemic and stochastic uncertainties associated with the model were quantified to aid target selection and further work. Main recommendations of this exercise are the following: (1) project-scale ground exploration for the Sung valley and Jasra complexes; (2) further regional-scale data collection for the Mikir Hills in the areas surrounding Samchampi and Barpung Complexes and around the swarms of dykes in the Garo Hills around Swangkre; (3) follow-up exploration in the areas north of Silchar and south of Nongstoin and (4) detailed geochemical sampling and surface or air-borne radiometric surveys for the Mawpyut Ultramafic Complex. The REE-mineral-systems model and the workflow demonstrated in this article could be used for targeting REE deposits in geologically similar terrains worldwide. [ABSTRACT FROM AUTHOR]

The purpose of the paper is to create an information, fuzzy risk assessment model to support the decision-making of Municipality management for the establishment and management of measures in the safe mode (regular) of City, emergency and disaster situations, in the selected components of Smart City concept. Research on this topic was motivated by the need for support, especially in emergency situations, such as the COVID-19 pandemic. It is proposed that the evaluation be carried out at local level within the framework of the Smart City concept and selected components integrated into the entity, including the Smart Security, Smart Healthcare, and Smart Environment components supported by the Smart WebGIS subsystem. The model also assesses proposed solutions for self-government financing to ensure the acceptable risk, and economic impact of decisions on the city budget within the Smart Budget aspects of selected components. Decision-making is based on intellectual analysis, processing of fuzzy data and use of fuzzy inference. The output of the model is the assessment of the risk of the municipality subsystems, taking into account the threshold for the functioning of the municipality subsystems, the linguistic interpretation of the level of risk and the acceptability of the tolerable risk resource. The model algorithm was used to create a web application to support the Municipal management for the above-mentioned agenda, from safe time to pandemics. • Municipality management and decision-making based on intellectual analysis, processing of fuzzy data, and use of fuzzy inference. • Assessment of the risk of the municipality selected subsystems within the Smart City concept. • Fuzzy mathematical risk assessment model was proposed to support decision-making according to an 8-step algorithm based on expert hybrid data, using linguistic and quantitative variables. • Model algorithm and web application to support the Municipal management from safe time to pandemics as COVID-19. • Smart Security, Smart Healthcare, and Smart Environment components supported by the Smart WebGIS subsystem. [ABSTRACT FROM AUTHOR]

This paper investigates the reduced-order filter design method for fuzzy Markov jump affine systems with dynamic event-triggered protocol and uncertain packet dropouts. Aiming at approximating the nonlinearities with high accuracy and broadening practical application, the fuzzy Markov jump affine systems associated with mode-dependent operating regions are developed. A novel nonhomogeneous Markov process is proposed to describe the generalized stochastic jumping among subsystems, whose time-varying transition probabilities are orchestrated by a higher-level deterministic switching signal. Compared with the conventional Markov process with arbitrary switchings, the average dwell-time strategy is adopted in the novel nonhomogeneous Markov process to improve the dynamic performance. A dynamic event-triggered protocol is provided to alleviate the network transmission burden by elongating the interval between any two consecutive events. Based on the variation of state-space partitions, nonsynchronous reduced-order generalized filters are considered. Under this framework, sufficient criteria are attained to ensure stochastic stability and prescribed l 2 − l ∞ performance for the filtering error systems. Eventually, the theoretical findings are verified by two simulation examples. [ABSTRACT FROM AUTHOR]

The paper presents a method of designing a fuzzy model for a nonlinear mechatronic system described only by input/output relations. The fuzzy model of the system is constructed on basis of the system's measured input/output data without the necessity of preliminary knowledge of its internal structure and parameters. In the first part of the paper we describe the method of the fuzzy model design in the simple example of third order nonlinear system, in the second part this method is applied to a real nonlinear dual axis mechatronic system. Important simulations and experimental measurements have been realized which confirm the rightness of the proposed fuzzy modelling method, which can also be applied for other nonlinear MIMO systems. [ABSTRACT FROM AUTHOR]

This note deals with the observer design for unknown inputs Takagi–Sugeno fuzzy systems with application in chaos synchronization and secure communications. Using Lyapunov method, sufficient synthesis conditions are given in Linear Matrix Inequalities (LMI) terms. The given design is then applied in a chaos synchronization and secure communication procedure where the plaintext (message) is encrypted using chaotic signals at the drive system side. The plaintext is retrieved via the designed unknown input observer. A pole placement in an LMI region is also considered to improve the observer performances. An illustrative example is given to show the effectiveness of the given design. [ABSTRACT FROM AUTHOR]

Abstract: The paper is concerned with the design of a fuzzy model-based predictive controller for activated sludge wastewater treatment processes. The control purpose is to maintain the dissolved oxygen concentration in an aerobic reactor of the wastewater treatment plant at the set-point. The fuzzy model of the activated sludge processes is derived based on the Activated Sludge Model No. 1 (ASM1), including the structure of the fuzzy rules. The required fuzzy space of input variables is partitioned by fuzzy c-means cluster algorithm and the consequent parameters are identified using the method of least squares. Compared with both traditional PID control and dynamic matrix control schemes, the proposed fuzzy model-based predictive control paradigm achieves satisfactory benefits in terms of both transient and steady performances. [Copyright &y& Elsevier]

Abstract: This paper develops a novel data-driven fuzzy modeling strategy and predictive controller for boiler–turbine unit using fuzzy clustering and subspace identification (SID) methods. To deal with the nonlinear behavior of boiler–turbine unit, fuzzy clustering is used to provide an appropriate division of the operation region and develop the structure of the fuzzy model. Then by combining the input data with the corresponding fuzzy membership functions, the SID method is extended to extract the local state-space model parameters. Owing to the advantages of the both methods, the resulting fuzzy model can represent the boiler–turbine unit very closely, and a fuzzy model predictive controller is designed based on this model. As an alternative approach, a direct data-driven fuzzy predictive control is also developed following the same clustering and subspace methods, where intermediate subspace matrices developed during the identification procedure are utilized directly as the predictor. Simulation results show the advantages and effectiveness of the proposed approach. [Copyright &y& Elsevier]

Abstract: System identification plays an important role in many fields of science and engineering. This paper deals with a new nonlinear identification method fit for supercharged boiler superheated steam pressure. The superheated steam pressure is influenced by fuel and superheated steam flow, whereas traditional identification methods always omit the influence of superheated steam flow, and receive limited identification precision due to the uncertain time delay and strong nonlinearity. Taking into account that Laguerre filters can approximate linear systems (even with time delay) with a model order lower than ARX model and fuzzy identification from measured data is effective enough to approximate uncertain nonlinear systems, Laguerre filters and fuzzy model are firstly combined into Hammerstein structure to construct Laguerre-Fuzzy Hammerstein model. The defined model is a two inputs single output model which considers both of the two nonlinear variables and can avoids the decrease of identification precision resulted by uncertain time delay. The proposed model is applied in the nonlinear identification of supercharged boiler superheated steam pressure. Simulation results show that the Laguerre-Fuzzy Hammerstein model can trace the process nonlinearity precisely and has higher prediction accuracy than ARX model and basic Hammerstein model with a lower model order. Moreover, Laguerre-Fuzzy Hammerstein model improves the computation efficiency and system stability greatly. [Copyright &y& Elsevier]

Abstract: This paper compares a fuzzy model, expressed in rule-form, with a well known statistical approach (i.e. logistic regression model) for diagnostic decision making in patients with chronic nasal symptoms. The analyses were carried out using a database obtained from a questionnaire administered to 1359 patients with nasal symptoms containing personal data, clinical data and skin prick test (SPT) results. Both the fuzzy model and the logistic regression model developed were validated using a data set obtained from another medical institution. The accuracy of the two models in identifying patients with positive or negative SPT was similar. This study is a preliminary step to the creation of a software that primary care doctors can use to make a diagnostic decision, when deciding whether patients with nasal symptoms need allergy testing or not. [Copyright &y& Elsevier]

Highlights: [•] A fuzzy model able to estimate indoor illuminance using measured or simulated external conditions. [•] The model shows good illuminance-estimation levels in comparison to indoor illuminance measurements. [•] To obtain the model, knowledge about the room geometry, surfaces, windows and furniture is not required. [•] The model can be used for simulation studies on living comfort, energy conservation and control design. [•] The model is simple to implement in any programming language by using a set of fuzzy rules. [ABSTRACT FROM AUTHOR]

From early 2020, a novel coronavirus disease pneumonia has shown a global "pandemic" trend at an extremely fast speed. Due to the magnitude of its harm, it has become a major global public health event. In the face of dramatic increase in the number of patients with COVID-19, the need for quick diagnosis of suspected cases has become particularly critical. Therefore, this paper constructs a fuzzy classifier, which aims to detect infected subjects by observing and analyzing the CT images of suspected patients. Firstly, a deep learning algorithm is used to extract the low-level features of CT images in the COVID-CT dataset. Subsequently, we analyze the extracted feature information with attribute reduction algorithm to obtain features with high recognition. Then, some key features are selected as the input for the fuzzy diagnosis model to the training model. Finally, several images in the dataset are used as the test set to test the trained fuzzy classifier. The obtained accuracy rate is 94.2%, and the F1-score is 93.8%. Experimental results show that, compared with the deep learning diagnosis methods widely used in medical image analysis, the proposed fuzzy model improves the accuracy and efficiency of diagnosis, which consequently helps to curb the spread of COVID-19. • Proposal of a deep fuzzy model for diagnosing COVID-19 using CT images. • Design of deep learning framework for extracting CT image features. • Attribute reduction algorithm is used to filter the features and extract the most expressed features. • The extracted features were used to train the fuzzy diagnosis model and optimize the model performance. • The training time and parameters of the model are less, so it has certain clinical value. [ABSTRACT FROM AUTHOR]

• The adaptability against uplink data loss for nonlinear plant is enhanced evidently. • An additional constraint is for the first time proposed for updating the plant status instantly. • A worse health quality of uplink channels can be affordable in this study. The problem of promoting the adaptability to uplink data loss for nonlinear plant is addressed via developing the fuzzy gain-scheduling stabilization law based on a novel online evaluation mechanism. Different from those previous methods, the proposed online evaluation mechanism is dependent not only the current-time but also the past-time normalized fuzzy weighting functions, and thus much more information can be absorbed and utilized in the process of stabilization synthesis by introducing extra free matrices than before. More importantly, an additional constraint is for the first time proposed for updating the plant status instantly so that critical replacement operations can be implemented for reducing the conservativeness of the designing conditions. Therefore, the adaptability to uplink data loss is improved evidently and thus the worse communication quality of uplink channel is bearable in this study. Finally, the advantages relative to those reported ones are tested and validated through benchmark numerical comparisons. [ABSTRACT FROM AUTHOR]

Highlights: [•] The integration of iterative learning control with a real-time state feedback model predictive control constitutes the model predictive iterative learning control (MPILC). [•] The nonlinear power plant dynamic is described by a fuzzy model which contains local liner models. [•] The fuzzy nonlinear model predictive controller based on iterative learning control (NMPILC) is constituted for a drum-type boiler–turbine system. [Copyright &y& Elsevier]

Abstract: This study investigates the demand-side control enhancement of TES though comparing the benchmark control strategies and newly-suggested adaptive MMPC designed to handle uncertainty in an adaptive fashion. Evaluations are performed through closed-loop simulations of an actual test building that is calibrated with real data and weather. While typical MPC centralizes computational burden (due to a provision for disturbances) on optimization through a single model, the adaptive MMPC distributes such burden (with less complexity) to multiple local models and optimizations in advance, then the online supervisory controller selects or interpolates the most adequate local models and control policies for the current conditions, thereby provides an effective global control policy for the entire operation regime. Building Energy Model (BEM) is used to construct local models for the adaptive MMPC, which enables more semantically feasible and acceptable model calibrations through which practitioners would obtain more model fidelity. This approach not only alleviates real time computation load, but also still achieves the desired performance. Evaluation results show that the adaptive MMPC outperforms the storage priority control and also ensures a near-optimal performance in load shifting under various uncertainty situations, including depreciation scenarios and unmeasured disturbance scenarios. [Copyright &y& Elsevier]