Hierarchical Fuzzy Model Research Articles

Unsupervised Image Classification Based on Fully Fuzzy Voronoi Tessellation

High noise resistance and high boundary fitting accuracy have always been the goals of image classification. However, the two mutually constrain each other, making it extremely difficult to reach equilibrium. To deal with this problem, the unsupervised image classification algorithm based on fully fuzzy Voronoi tessellation is proposed. It extends Voronoi tessellation from hard to fuzzy, and proposes a hierarchical fuzzy membership model, i.e., pixels fuzzily belong to Voronoi polygons and polygons fuzzily belong to clusters. The objective function is established based on the hierarchical fuzzy membership model by fully considering the transitivity of fuzziness between different levels. Then, the optimal classification result can be obtained by the fuzzy comprehensive decision theory under the best parameter solution. The first level retains the flexibility of pixels while modeling spatial constraints. The second level determines which class the polygon belongs to under the constraint of the first level. It provides an effective way of balancing noise resistance and boundary fitting. In addition, the Voronoi tessellation is explicitly expressed in the objective function in the form of the mathematical model, which allows it to obtain the optimal value through analytical solutions instead of the previous random sampling method. It greatly increases the convergence speed of the algorithm. Experiments have been performed on simulated and several remote sensing images with seven comparing algorithms to demonstrate the effectiveness of the proposed algorithm.

Clinical decision support system using hierarchical fuzzy diagnosis model for migraine and tension-type headache based on International Classification of Headache Disorders, 3rd edition.

To determine whether the diagnostic ability of the newly designed hierarchical fuzzy diagnosis method is consistent with that of headache experts for probable migraine (PM) and probable tension-type headache (PTTH). Clinical decision support systems (CDSS) are computer systems designed to help doctors to make clinician decisions by information technology, and have proven to be effective in improving headache diagnosis by making medical knowledge readily available to users in some studies. However, one serious drawback is that the CDSS lacks the ability to deal with some fuzzy boundaries of the headache features utilized in diagnostic criteria, which might be caused by patients' recall bias and subjective bias. A hybrid mechanism of rule-based reasoning and hierarchical fuzzy diagnosis method based on International Classification of Headache Disorders, 3rd edition (ICHD-3) was designed and then validated by a retrospective study with 325 consecutive patients and a prospective study with 380 patients who were clinically diagnosed with migraine and TTH at the headache clinic of Chinese PLA General Hospital. The results of the diagnostic test in the retrospective study indicated that the fuzzy-based CDSS can be used in the diagnosis of migraine without aura (MO) (sensitivity 97.71%, specificity 100%), TTH (sensitivity 98.57%, specificity 100%), PM (sensitivity 91.25%, specificity 98.75%) and PTTH (sensitivity 90.91%, specificity 99.63%). While in the prospective study, the diagnostic performances were MO (sensitivity 91.62%, specificity 96.52%), TTH (sensitivity 92.17%, specificity 95.47%), PM (sensitivity 85.48%, specificity 98.11%) and PTTH (sensitivity 87.50%, specificity 98.60%). Cohen's kappa values for the consistency test were 0.984 ± 0.018 (MO), 0.991 ± 0.018 (TTH), 0.916 ± 0.051 (PM), 0.932 ± 0.059 (PTTH) in the retrospective study and 0.884 ± 0.047 (MO), 0.870 ± 0.055 (TTH), 0.853 ± 0.073 (PM), 0.827 ± 0.118 (PTTH) in the prospective study, which indicated good consistency with the fuzzy-based CDSS and the gold standard (p < 0.001). We developed a fuzzy-based CDSS performs much more similarly to expert diagnosis and performs better than the routine CDSS method in the diagnosis of migraine and TTH, and it could promote the application of artificial intelligence in the area of headache diagnosis.

Hierarchical fuzzy model applied to oil trading

Computer trading is currently relatively limited to quantitative trading in paper markets, such as, futures, swaps, and options, ignoring the large volume of physical commodities trading. Numerical algorithms and mathematical methods are frequently applied in the trading of non-physical commodities and stock markets. However, the physical trade of oil does not have a computer program that represents an unquestionable development that includes more complex and subjective factors that traders take into consideration when entering a transaction. Using fuzzy logic, this work proposes a new approach to base a method that can rank oils and the variables, commonly involved in the trading. It uses fuzzy logic to blend objective and subjective factors and brings in two key hierarchical steps to the process. It is shown that this model can also be useful for apprising a decision-making process, improving internal communication, and for the management of physical commodities trading. Here the options of trading are assessed accordingly to its numerical and linguistic judgments, considering even abrupt outcomes. The wide-ranging options, successive filters, and factors evaluation that mirror the technical and expert trading decision making process make it possible for the future application of artificial intelligence (AI) in physical commodities trading.

Hierarchical Fuzzy MCDA Multi-Risk Model for Detecting Critical Urban Areas in Climate Scenarios

One of the issues of greatest interest in urban planning today concerns the evaluation of the most vulnerable urban areas in the presence of different types of climate hazards. In this research, a hierarchical fuzzy MCDA model is implemented on a GIS-based platform aimed at detecting the urban areas most at risk in the presence of heatwave and pluvial flooding scenarios. The proposed model aims to detect the urban areas most vulnerable to both the two climatic phenomena and the two types of hazards as independent events; it partitions the physical component of an urban settlement into two subsystems: buildings and open spaces, and it determines the criticality of a subzone of the urban area of study by evaluating the vulnerabilities of the two subsystems to the two phenomena. The use of a hierarchical fuzzy MCDA model facilitates the modeling of the two subsystems and the assessment of their vulnerability to the two phenomena, and it provides a computationally fast tool for detecting critical urban areas. The model was tested on a study area made up of the districts of the central-eastern area of the city of Naples (Italy); it was divided into subzones made up of individual census areas. The most critical areas are represented by the subzones with criticality values higher than a specific threshold.

Hierarchical fuzzy DEA model with double frontiers combined with TOPSIS technique: application on mobile money agents locations

Hierarchical fuzzy DEA model with double frontiers combined with TOPSIS technique: application on mobile money agents locations

Hierarchical fuzzy comprehensive evaluation of prevention and control level of occupational hazards in coal mines

Objective: To establish an evaluation model for occupational hazard prevention and control levels in coal mines, to explore the combination of Analytic Hierarchy Process (AHP) and fuzzy comprehensive evaluation, to evaluate the overall situation of occupational hazard prevention and control in coal mines. Methods: In November 2021, Collect information of occupational hazards and their prevention and control status in 30 coal mines. AHP model was first constructed for the elements of occupational hazard prevention and control in coal mines. Then, the AHP and fuzzy comprehensive evaluation method was applied to comprehensively evaluate and grade the occupational hazard prevention and control in coal mines, using the principles of maximum membership and weighted average. Results: The hierarchical fuzzy comprehensive evaluation results for typical coal mine were basically consistent with its occupational hazard prevention and control situation. The dust prevention and control situation was good, the noise prevention and control situation is average, the occupational health monitoring situation was good, the occupational health management situation was average, and the overall level of occupational hazard prevention and control was good. Conclusion: The hierarchical fuzzy comprehensive evaluation model for occupational hazard prevention and control levels, combined with the principles of maximum membership and weighted average, can objectively evaluate and reflect the overall situation of occupational hazard prevention and control in coal mines.

Topology structure optimization of evolutionary hierarchical fuzzy systems

In this paper, a new method of hierarchical fuzzy system modeling for high-dimensional regression problems is proposed, which is called multi-objective evolutionary hierarchical fuzzy regression system (MOEHFRS). Different from the existing hierarchical fuzzy systems with fixed topology, the proposed MOEHFRS improves the accuracy of the model, reduces the total number of rules, and eliminates unnecessary features by flexibly constructing topology. In the process of topology evolution, MOEHFRS can exchange and combine different sub-fuzzy systems to achieve the selection and reuse of important features, as well as the elimination of unnecessary features, which improves the diversity of topology and enables the model to be well applied to high-dimensional regression problems. Different combinations of sub-fuzzy systems will result in different performance and number of rules. A new multi-objective evolutionary optimization algorithm is proposed to simultaneously optimize the number of rules and the accuracy of the model, which achieves the balance between complexity and accuracy of MOEHFRS. The proposed method is validated on 13 real world regression datasets and compared with other 5 methods. The results show that MOEHFRS is effective and advanced in terms of accuracy, number of rules, retention of important features and universality in different regression problems.

Drinking Water Quality Assessment Using a Fuzzy Inference System Method: A Case Study of Rome (Italy).

Drinking water quality assessment is a major issue today, as it is crucial to supply safe drinking water to ensure the well-being of society. Predicting drinking water quality helps strengthen water management and fight water pollution; technologies and practices for drinking water quality assessment are continuously improving; artificial intelligence methods prove their efficiency in this domain. This research effort seeks a hierarchical fuzzy model for predicting drinking water quality in Rome (Italy). The Mamdani fuzzy inference system is applied with different defuzzification methods. The proposed model includes three fuzzy intermediate models and one fuzzy final model. Each model consists of three input parameters and 27 fuzzy rules. A water quality assessment model is developed with a dataset that considers nine parameters (alkalinity, hardness, pH, Ca, Mg, fluoride, sulphate, nitrates, and iron). These nine parameters of drinking water are anticipated to be within the acceptable limits set to protect human health. Fuzzy-logic-based methods have been demonstrated to be appropriate to address uncertainty and subjectivity in drinking water quality assessment; they are an effective method for managing complicated, uncertain water systems and predicting drinking water quality. The proposed method can provide an effective solution for complex systems; this method can be modified easily to improve performance.

Risk Assessment of an Existing Metro Tunnel in Close Proximity to New Shield Tunnels following Construction

The construction of a new shield tunnel near an existing operating tunnel poses a great risk to the existing tunnel structure due to the continuous encryption of the rail transit network. This study investigated the safety status of an existing metro tunnel in close proximity to new shield tunnels following construction. A fuzzy comprehensive assessment model (hierarchical fuzzy comprehensive evaluation model) based on an analytic hierarchy process was proposed to assess the risks of the existing tunnel structure. The threshold of indicators in the existing tunnel structure risk assessment system was determined based on the tunnel function and structure security. Then, we described the membership vector determination method, weight vector determination method, and comprehensive evaluation vector processing method. Taking a project case in China as the research object, the quantitative analysis of the established evaluation system was carried out, and the intuitive risk assessment results were obtained. The hierarchical fuzzy comprehensive evaluation model can be employed as a decision-making tool for newly built shield tunnels passing through the existing tunnels, which can provide guidance for tunnel maintenance and guarantee.

A Computational Model for Driver Risk Evaluation and Crash Prediction Using Contextual Data from On-board Telematics

Introduction: Vehicle crashes can be hazardous to public safety and may cause infrastructure damage. Risky driving significantly raises the possibility of the occurrence of a vehicle crash. As per statistics by the World Health Organization (WHO), approximately 1.35 million people are involved in road traffic crashes resulting in loss of life or physical disability. WHO attributes events like over-speeding, drunken driving, distracted driving, dilapidated road infrastructure and unsafe practices such as non-use of helmets and seatbelts to road traffic accidents. As these driving events negatively affect driving quality and enhance the risk of a vehicle crash, they are termed as negative driving attributes. Methods: A multi-level hierarchical fuzzy rules-based computational model has been designed to capture risky driving by a driver as a driving risk index. Data from the onboard telematics device and vehicle controller area network is used for capturing the required information in a naturalistic way during actual driving conditions. Fuzzy rules-based aggregation and inference mechanisms have been designed to alert about the possibility of a crash due to the onset of risky driving. Results: On-board telematics data of 3213 sub-trips of 19 drivers has been utilized to learn long term risky driving attributes. Furthermore, the current trip assessment of these drivers demonstrates the efficacy of the proposed model in correctly modeling the driving risk index of all of them, including 7 drivers who were involved in a crash after the monitored trip. Conclusions: In this work, risky driving behavior has been associated not just with rash driving but also other contextual data like driver’s long-term risk aptitude and environmental context such as type of roads, traffic volume and weather conditions. Trip-wise risky driving behavior of six out of seven drivers, who had met with a crash during that trip, was correctly predicted during evaluation. Similarly, for the other 12 drivers, the model accurately predicted safe driving behavior as these drivers did not meet with any vehicle crash. The proposed model can be used as an alert mechanism to indicate potential crash scenarios to the driver. The current study did not study lane changing behavior in detail due to difficulty in capturing road lanes in the Indian context.

A Fuzzy Multi-Criteria Model for Municipal Waste Treatment Systems Evaluation including Energy Recovery

One of the recent problems on waste sorting systems is their performance evaluation for proper decision making and management. For this purpose, multi-criteria methods can be used to evaluate the sorting system from both operational and financial perspectives. According to a recent literature review, there are no solutions for evaluating waste sorting systems that take into account: sorting point utilisation, sorting efficiency, waste stream irregularity, and technical system availability. In addition, the problem of data uncertainty and the need to use expert judgements indicate the need for the implementation of methods adjusted to the qualitative and quantitative assessment, such as the fuzzy approach. Following this, in order to overcome the presented limitations, the authors introduced the new assessment method for waste sorting systems based on multi-criteria model implementation and fuzzy theory use. Therefore, the developed model was based on a hierarchical fuzzy logic model for which appropriate membership function parameters and inference rules were defined. The specificity of the chosen assessment criteria and their justification was provided. The model has been implemented to evaluate one of the waste sorting plants in Wroclaw, Poland. Tests have been conducted for seven different configurations of waste sorting lines (with variable input parameters). The study focuses on analysing the amount of selected waste at each station in relation to the total stream size of each fraction. Efficiency was measured by the mass of the collected waste and the number of pieces of waste in each fraction. Based on the obtained results, estimations of particular parameters of the model were made, and the results were presented and commented on. It was shown that there is a significant relationship between the level of system evaluation and sorting efficiency and an inverse relationship with the level of RDF obtained. The analysis was based on Pearson’s linear correlation coefficient estimation and linear regression implementation.

The hierarchical fuzzy model of hydro acoustic activity for underwater vehicles

The description of the basic equations and numerical-analytical methods of analysis of the theoretical model of functioning and structural-parametric optimization of hydro acoustic screens of underwater vehicles. The technique is based on a hierarchical fuzzy model of hydro acoustic activity underwater vehicles.

Change Detection from SAR Images Based on Convolutional Neural Networks Guided by Saliency Enhancement

Change detection is an important task in identifying land cover change in different periods. In synthetic aperture radar (SAR) images, the inherent speckle noise leads to false changed points, and this affects the performance of change detection. To improve the accuracy of change detection, a novel automatic SAR image change detection algorithm based on saliency detection and convolutional-wavelet neural networks is proposed. The log-ratio operator is adopted to generate the difference image, and the speckle reducing anisotropic diffusion is used to enhance the original multitemporal SAR images and the difference image. To reduce the influence of speckle noise, the salient area that probably belongs to the changed object is obtained from the difference image. The saliency analysis step can remove small noise regions by thresholding the saliency map, and interest regions can be preserved. Then an enhanced difference image is generated by combing the binarized saliency map and two input images. A hierarchical fuzzy c-means model is applied to the enhanced difference image to classify pixels into the changed, unchanged, and intermediate regions. The convolutional-wavelet neural networks are used to generate the final change map. Experimental results on five SAR data sets indicated the proposed approach provided good performance in change detection compared to state-of-the-art relative techniques, and the values of the metrics computed by the proposed method caused significant improvement.

Evolution of a hybrid approach for groundwater vulnerability assessment using hierarchical fuzzy-DRASTIC models in the Cuddalore Region, India

Uncertainty in the supply and demand and a lack of available freshwater resources require a better management plan for sustainable development in agriculturally dependent communities. Therefore, scarce freshwater resources are protected and monitored to prevent contamination. Groundwater is the largest freshwater reservoir, and groundwater zones prone to contamination need to be identified. A precise model that enables the simplification and validation of the assessment process was developed by applying a fuzzy logic technique. A hierarchical fuzzy inference model (HFIM) was developed to better handle the input. The application of the developed model was then compared with the conventional index-based DRASTIC model in the Cuddalore District. The parameters that were found to influence the degree of vulnerability, including the depth of the water table (D), net recharge to the aquifer (R), aquifer media (A), soil properties (S), topography of the area (T), impact of the vadose zone (I), and hydraulic conductivity of the aquifer (C), were considered in the model development. A geographical information system (GIS) framework was utilized to synthesize the DRASTIC model and MATLAB was employed to develop the hierarchical fuzzy inference model. The results obtained from the GIS-DRASTIC model and HFIM were classified into five and seven categories based on their index values, respectively. The models were validated using nitrate concentration (mg/l) data obtained from 40 sampling points in and around the study area. A sensitivity analysis was performed on the models by varying the input from their minimum to maximum values for a selected hydrogeological setting. The results revealed that the HFIM was better at determining groundwater vulnerability levels in the Cuddalore District. It could cope with the uncertainty and nonlinearity of the datasets; the output showed a continuous response to modifications of the input data, which contrasts the DRASTIC model.

Algorithms for Creating the Digital Twin of a Distributed Generator

The article describes the concept of a digital twin of a distributed generator (DG) implemented on the basis of a salient-pole synchronous generator. The structure of the digital twin is presented in the form of a hierarchical fuzzy model built on the experimental data. For building fuzzy models of individual elements and links of a generator, software algorithms for optimization of the membership functions of term sets and the numbers of knowledge base rules are proposed. The results of experiments on obtaining an optimized neuro-fuzzy model for regulating the rotation speed of the generator rotor are presented. A comparative analysis of the oscillograms of the output signal of the optimized fuzzy model showed a sufficiently high accuracy when using the subtractive clustering method to build a fuzzy logic system. This approach made it possible to significantly reduce the number of term sets and the amount of the fuzzy model rules. The proposed algorithms can be used in further research aimed at industrial implementation of DG digital twins, as well as for solving the problem of tuning automatic regulators of low-power synchronous generators

A hierarchical fuzzy data envelopment analysis for wind turbine site selection in Indonesia

The Indonesian archipelago has several suitable areas for building wind farms. In the site selection process, apart from wind intensity, there are other factors related to geographical and structural technicality that need to be considered. This research presents a hierarchical fuzzy data envelopment analysis model for identifying suitable locations for the construction of wind farms. The proposed hierarchy consists of two levels that are defined based on the 165 districts and 33 provinces in Indonesia based on data provided by different government organizations. Opinions from experts in different areas were collected and represented by the hesitant fuzzy linguistic term sets, which were converted to optimistic and pessimistic preferences by using linguistic aggregation and, later, integrated to the data envelopment analysis model. Principal component analysis by IBM SPSS was used to verify the importance of the factors that can reduce ineffective indicators from the analysis. The results show that the South Sumatra province has the highest potential for construction of wind farms, especially in the district of Palembang. The West Papua, Papua, and Maluku provinces have descending priority based on good infrastructure accessibility, high wind velocity, and lesser susceptibility to natural disasters.

Bidirectional approximate reasoning-based approach for decision support

Fuzzy rule-based systems are widely applied for real-world decision support, such as policy formation, public health analysis, medical diagnosis, and risk assessment. However, they face significant challenges when the application problem at hand suffers from the “curse of dimensionality” or “sparse knowledge base”. Combination of hierarchical fuzzy rule models and fuzzy rule interpolation offers a potentially efficient and effective approach to dealing with both of these issues simultaneously. In particular, backward fuzzy rule interpolation (B-FRI) facilitates approximate reasoning to be performed given a sparse rule base where rules do not fully cover all observations or the observations are not complete, missing antecedent values in certain available rules. This paper presents a hierarchical bidirectional fuzzy reasoning mechanism by integrating hierarchical rule structures and forward/backward rule interpolation. A computational method is proposed, building on the resulting hierarchical bidirectional fuzzy interpolation to maintain consistency in sparse fuzzy rule bases. The proposed techniques are utilised to address a range of decision support problems, successfully demonstrating their efficacy.

Generating a hierarchical fuzzy rule-based model

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.

Quality Evaluation Fuzzy Method of Automated Control Systems on the LMS Example

Software products are progressing rapidly and they are serve humans virtually in all spheres of life. Education is facing the same process. Consequently, evaluation of quality of a software product has become an important task for prevalent number of organizations. Several models have been proposed to help different types of users with quality problems. Development of software construction methods has influenced the creation of models for evaluating the quality. This paper describes a graph of the development of software quality models, as well as newly determined characteristics for creating a new model. The given paper proposes a new hierarchical four-level fuzzy model for evaluating software quality. A new method for evaluating the quality of the software is also described in the example of automated control systems or ERP systems (on the example of learning management systems). The proposed new model for evaluating software quality was software implemented with use of fuzzy logic. Through the number of experiments, we scrutinized quality evaluation of various software products. The proposed method should solve the problem of achieving quality in complex of development systems.

A Nested Tensor Product Model Transformation

The tensor product model transformation (TPMT) is an emerging numerical framework of the Takagi–Sugeno (T–S) fuzzy (or polytopic) system modeling for a linear matrix inequality based system control design. A nested TPMT (NTPMT) is proposed in this paper, which merges the dimensions of the tensors and performs the TPMT iteratively. The resultant fuzzy model is in a multilevel nested tensor product (TP) structure. The vertex tensor obtained by NTPMT has fewer dimension results than the original TPMT so the number of vertices or fuzzy rules, which have been the main bottleneck for further application of the TPMT in higher dimensional systems, is expected to decrease significantly. It is also proven that the NTPMT contains the hierarchical fuzzy logic, meaning that the NTPMT is capable of conducting hierarchical fuzzy modeling and reduction. Furthermore, because the inclusion of multiple TPMTs is prone to augment the conservativeness of the resultant fuzzy model, a suboptimal convex hull rectification algorithm for the TPMT is developed based on a newly defined tightness measure, and then extended to render the NTPMT as less conservative as possible. Finally, numerical simulations on two real physical systems (two- and four-parameter dimension) are verified to demonstrate the performance of the methods.