Fuzzy Cognitive Map Model Research Articles

Modelling Differential Diagnosis of Febrile Diseases with Fuzzy Cognitive Map.

The report of the World Health Organization (WHO) about the poor accessibility of people living in low-to-middle-income countries to medical facilities and personnel has been a concern to both professionals and nonprofessionals in healthcare. This poor accessibility has led to high morbidity and mortality rates in tropical regions, especially when such a disease presents itself with confusable symptoms that are not easily differentiable by inexperienced doctors, such as those found in febrile diseases. This prompted the development of the fuzzy cognitive map (FCM) model to serve as a decision-support tool for medical health workers in the diagnosis of febrile diseases. With 2465 datasets gathered from four states in the febrile diseases-prone regions in Nigeria with the aid of 60 medical doctors, 10 of those doctors helped in weighting and fuzzifying the symptoms, which were used to generate the FCM model. Results obtained from computations to predict diagnosis results for the 2465 patients, and those diagnosed by the physicians on the field, showed an average of 87% accuracy for the 11 febrile diseases used in the study. The number of comorbidities of diseases with varying degrees of severity for most patients in the study also covary strongly with those found by the physicians in the field.

MODEL FCM JAKO METODA ZARZĄDZANIA PRZESTRZENIĄ PUBLICZNĄ

The work presents the results of research that focus on creating high-quality public space through the involvement of society and taking into account the opinions of various stakeholder groups. The main goal is to understand how the concepts of "man-space-management" can be integrated in the process of creating high-quality public places in accordance with the principles of UN-Habitat. An important research aspect is the development of FCM (Fuzzy Cognitive Maps) models and various scenarios for the development of public space, which will enable the effective use of financial resources by the government, non-governmental organizations and private investors. The research is based on the opinions of the Zielona Góra community, which were collected through "placegame" workshops and questionnaires.

Smart heat tariffs in transition to free market

Innovative pricing mechanisms should motivate heat suppliers and consumers to move toward more sustainable energy systems and introduce low-temperature district heating systems and sector coupling in smart energy systems. Therefore, district heating regulation regimes should also be changed to stimulate transformations in the energy sector. The district heating tariffs depend on many factors, including fuel prices, operational parameters, taxes, investments, and other criteria. Therefore, an analysis of the DH tariffs has been implemented to find solutions to motivate DH enterprises towards energy efficiency and climate neutrality. The analysis results are based on the decision-making assessment approach by selecting various criteria and evaluating them from five significant aspects: engineering, environmental, climate, economic and socioeconomic. The central elements within the developed fuzzy cognitive mapping model are investment costs, heat production costs, and primary energy consumption. Considering the set boundary conditions, the most beneficial method for smart heat tariff definition could be heat tariff benchmarking with integrated energy efficiency standards for DH operators.

Risk measurement and application of the international carbon market in the era of global conflict: A data-driven study using FCM

The accurate measurement and effective estimation of carbon market risk are crucial for practitioners and policymakers to mobilize resources toward the transition to a climate-resilient economy, particularly in a new era of global conflict. However, existing studies that have explored factors contributing to carbon market risk primarily relied on experience or subjective judgment in selecting risk-related factors. Such approaches undermine the estimation accuracy while making it difficult to ascertain causal inferences related to the risk spillover. To fill the gap, we adopted a data-driven factor analysis strategy by introducing the Fuzzy Cognitive Maps (FCM) model to establish a carbon market network and identify risk-related factors. We then evaluate the carbon market's risk level and spillover effects using combined econometric methods and explore their application in portfolio management. We report three main findings. First, based on our sample of 3217 observations between 2008 and 2022, five factors influencing carbon market risk emerged from the FCM, including OIL, COAL, SP500ENERGY, SPCLEANENERGY, and GPR. Second, we find a notable rise in risk spillover from GPR to EUA during the Russia-Ukraine conflict and an escalation of total cross-market spillover during extreme events. Third, our study presents new evidence on the hedging effect for EUA of the SP500ENERGY before the Russia-Ukraine conflict and of the SPCLEANENERGY during the conflict. Finally, implications are discussed for policymakers and investors.

Spatiotemporal Hybrid Air Pollution Early Warning System of Urban Agglomeration Based on Adaptive Feature Extraction and Hesitant Fuzzy Cognitive Maps

Long-term exposure to air pollution will pose a serious threat to human health. Accurate prediction can help people reduce exposure risks and promote environmental pollution control. However, most previous studies have ignored the spatial spillover of air pollution, i.e., that the current region’s air quality is also correlated with that of geographically adjacent areas. Therefore, this paper proposes an innovative spatiotemporal hybrid early warning system based on adaptive feature extraction and improved fuzzy cognition maps. Firstly, a spatial spillover analysis model based on the Moran index and local gravitational clustering was proposed to capture the diffusion and concentration characteristics of air pollution between regions. Then, an adaptive feature extraction model based on an optimized Hampel filter was put forward to process and correct the outliers in the original series. Finally, a hesitant fuzzy information optimized fuzzy cognitive maps model was proposed to forecast the air quality of urban agglomeration. The experimental results show that the air quality forecasting accuracy of urban agglomerations can be significantly improved when the geographical conditions and other interactions among cities are comprehensively considered, and the proposed model outperformed other benchmarks and can be used as a powerful analytical tool during urban agglomeration air quality management.

Modelling Stakeholders’ Knowledge and Perception in a Fuzzy Cognitive Map: The Case of the Extra-Virgin Olive Oil (EVOO) Value Chain in Central Italy

Italy is the second largest extra-virgin olive oil (EVOO) producer within the European Union. Despite its importance in preserving rural landscape and in supporting household economy, the EVOO sector faces several constraints due to high management costs, small farm size, lack of cooperation and investment, production vulnerability, and farmers’ ageing. Such a number of weak points suggests the need to identify and adopt innovative approaches, at both the farm and oil mill levels. In order to address these priorities, a fuzzy cognitive mapping (FCM) survey was carried out in Umbria region, central Italy, involving key local stakeholders of the EVOO value chain in the Orvieto district. Based on stakeholders’ perception and knowledge, this paper aims to identify and evaluate the most relevant components of the local olive oil value chain, and predict scenarios responding to hypothetical changes of the same components. These stakeholders were firstly invited to each build an individual fuzzy cognitive map and then, grouped all together, build a joint fuzzy cognitive map. Finally, the maps represented both the individual and the grouped stakeholders’ perceptions. The maps were translated into adjacency matrices in order to create an FCM model by applying the software “Mental Modeler”. In total, 24 participants, including practitioners, multipliers, researchers, suppliers and members of local administration, participated in the survey. The component analysis and the scenario analysis highlighted several priority issues: to preserve the ecosystem functioning, to implement cooperation, innovation and education, to adapt and mitigate climate change. The main novelty of this study is that all stakeholders’ categories in the EVOO sector recognize several challenges to sustain the EVOO value chain, in particular, climate change adaptation and mitigation.

An Integrated Scheme of the Data-Driven Multi-Block FCMs for Modeling the Steady Turning Motion of Motorboats

The steady turning motion of merchant ships is modeled according to industry specifications. However, challenges arise when motorboats are modeled. This study proposes a novel data-driven multi-block fuzzy cognitive map (FCM) model trained based on sea trials with four ship states. The optimal positions sampled by two different types of sensors were modeled using inverse variance weighting, which takes both Cartesian coordinate transformation and the constraints of the locations of the apparatuses into consideration. Combining these samplings with a scheme of multi-block FCMs, we conducted a study on data from motorboat trials. Our results closely approximate the data from motorboat trials at sea and are validated by a generated dataset of the classical model. Furthermore, we reveal the characteristics of our scheme, including the number of data blocks, the boundary of each block, and the parameters of the FCM for each block. As opposed to the classical method, the proposed scheme is insensitive to speed. This study presents a promising step toward mining modeling information from ship trials.

Fuzzy Cognitive Map-Driven Comprehensive Time-Series Classification.

This article presents a comprehensive approach for time-series classification. The proposed model employs a fuzzy cognitive map (FCM) as a classification engine. Preprocessed input data feed the employed FCM. Map responses, after a postprocessing procedure, are used in the calculation of the final classification decision. The time-series data are staged using the moving-window technique to capture the time flow in the training procedure. We use a backward error propagation algorithm to compute the required model hyperparameters. Four model hyperparameters require tuning. Two are crucial for the model construction: 1) FCM size (number of concepts) and 2) window size (for the moving-window technique). Other two are important for training the model: 1) the number of epochs and 2) the learning rate (for training). Two distinguishing aspects of the proposed model are worth noting: 1) the separation of the classification engine from pre- and post-processing and 2) the time flow capture for data from concept space. The proposed classifier joins the key advantage of the FCM model, which is the interpretability of the model, with the superior classification performance attributed to the specially designed pre- and postprocessing stages. This article presents the experiments performed, demonstrating that the proposed model performs well against a wide range of state-of-the-art time-series classification algorithms.

Applying Fuzzy Cognitive Map Based on Structural Equation Modeling for Perceiving the Service Quality and Attributes in Service Industry

<p>This study explores why the business firm survival due to provide the service quality and perceived values since servicescape, waiting experiences and food quality are three major factors that affect customer intentions. Therefore, the most examined restaurant attributes are included physical setting and environment, wait time, and food and service quality in this study. Servicescape positively effects perceived service quality. However, service quality is an overall judgment that a based on the perception of the object in consumer process of customer and can be seen as the result of customer evaluation. Therefore, we analyze data from 396 full-service restaurant diners in Taiwan based on Fuzzy Cognitive Map (FCM) and Structural Equation Model (SEM) to investigate hypothesis and to identify the most relevant decision factors to enhance outcome variables and furthers to help decision makers have a clear picture of affecting factors in the customer behavioral intention. The findings support the model and show that perceived overall service quality and perceived value do exert mediating effects in the relationship between restaurant-related attributes and customer behavioral intention. This study could ultimately contribute to the business firms in service industry to provide decision makers the most desirable outcomes to survival the competitive society.</p> <p> </p>

Cat Swarm with Fuzzy Cognitive Maps for Automated Soil Classification

Accurate soil prediction is a vital parameter involved to decide appropriate crop, which is commonly carried out by the farmers. Designing an automated soil prediction tool helps to considerably improve the efficacy of the farmers. At the same time, fuzzy logic (FL) approaches can be used for the design of predictive models, particularly, Fuzzy Cognitive Maps (FCMs) have involved the concept of uncertainty representation and cognitive mapping. In other words, the FCM is an integration of the recurrent neural network (RNN) and FL involved in the knowledge engineering phase. In this aspect, this paper introduces effective fuzzy cognitive maps with cat swarm optimization for automated soil classification (FCMCSO-ASC) technique. The goal of the FCMCSO-ASC technique is to identify and categorize seven different types of soil. To accomplish this, the FCMCSO-ASC technique incorporates local diagonal extrema pattern (LDEP) as a feature extractor for producing a collection of feature vectors. In addition, the FCMCSO model is applied for soil classification and the weight values of the FCM model are optimally adjusted by the use of CSO algorithm. For examining the enhanced soil classification outcomes of the FCMCSO-ASC technique, a series of simulations were carried out on benchmark dataset and the experimental outcomes reported the enhanced performance of the FCMCSO-ASC technique over the recent techniques with maximum accuracy of 96.84%.

Testing management scenarios for the North Sea ecosystem using qualitative and quantitative models

Abstract The complexities of ecosystem-based management require stepwise approaches, ideally involving stakeholders, to scope key processes, pressures, and impact in relation to sustainability and management objectives. Use of qualitative methods like Fuzzy Cognitive Mapping (FCM) with a lower skill and data threshold than traditional quantitative models afford opportunity for even untrained stakeholders to evaluate the present and future status of the marine ecosystems under varying impacts. Here, we present the results applying FCM models for subregions of the North Sea. Models for the southern North Sea, Skagerrak, Kattegat, and the Norwegian Trench were developed with varying level of stakeholder involvement. Future scenarios of increased and decreased fishing, and increased seal biomass in the Kattegat, were compared with similar scenarios run on two quantitative ecosystem model. Correspondence in response by the models to the same scenarios was lowest in the southern North Sea, which had the simplest FCM model, and highest in Norwegian Trench. The results show the potential of combining FCM and quantitative modelling approaches in integrated ecosystem assessments (IEAs) and in future ecosystem-based management advice, but to facilitate such comparisons and allow them to complement and enhance our IEAs, it is important that their components are aligned and comparable.

Time series forecasting using fuzzy cognitive maps: a survey

Among various soft computing approaches for time series forecasting, fuzzy cognitive maps (FCMs) have shown remarkable results as a tool to model and analyze the dynamics of complex systems. FCMs have similarities to recurrent neural networks and can be classified as a neuro-fuzzy method. In other words, FCMs are a mixture of fuzzy logic, neural network, and expert system aspects, which act as a powerful tool for simulating and studying the dynamic behavior of complex systems. The most interesting features are knowledge interpretability, dynamic characteristics and learning capability. The goal of this survey paper is mainly to present an overview on the most relevant and recent FCM-based time series forecasting models proposed in the literature. In addition, this article considers an introduction on the fundamentals of FCM model and learning methodologies. Also, this survey provides some ideas for future research to enhance the capabilities of FCM in order to cover some challenges in the real-world experiments such as handling non-stationary data and scalability issues. Moreover, equipping FCMs with fast learning algorithms is one of the major concerns in this area.

Research on behaviour planning for power substation inspection robot based on fuzzy cognitive map

A fuzzy cognitive map based behavior planning method for mobile robot is proposed in this paper. Aiming at the intelligentialize advanced application problems of power substation equipment inspection robot, a logical structure of inspection tasks planning based on hierarchical hybrid complex system is presented, and the operating principle of task decomposition and task planning are given in detail. The dependent events in inspecting tasks are considered as concept nodes to present the connection weights between nodes and establish the fuzzy cognitive map model of task and behavior planning, so as to realize task decomposition and generate the action logic sequences. Meanwhile, the action sequences can be adjusted in real time with the sensor information. The proposed method is simple without introducing complicated calculations and much training. Simulation results verify the feasibility and effectiveness.

Probabilistic linguistic fuzzy cognitive maps: applications to the critical factors affecting the health of rural older adults

BackgroundAchieving healthy ageing has become the only way for China to alleviate the pressure of ageing, especially in rural areas. However, the factors affecting the health of rural older adults are numerous and complex. It is important to identify the critical factors that affecting the health of older adults in rural areas and provide decision-making support for targeted health interventions.MethodsTo overcome some limitations of existing works, an extended probabilistic linguistic fuzzy cognitive map model is proposed in this paper as a useful tool for modeling the cause-effect relationship between factors. The proposed model integrates the advantages of probabilistic linguistic term sets and fuzzy cognitive maps. In the end, to rank and identify the critical factors affecting the health, a novel similarity measure based on Euclidean distance and Z-mapping function is proposed.ResultsThe proposed model can effectively deal with the uncertainty of experts and reflect different opinions of groups well. In terms of representing uncertainty and ambiguity, the proposed method outperforms other models in modeling complex systems. In the real-world case analysis, we find that education is the most important factor affecting the health of rural older adults, followed by previous occupational experiences, psychology, and physical exercise, among other things. Intergenerational relationship has become another important factor affecting the health of rural older adults in China as the development of Chinese society.ConclusionsFrom a macro perspective, social economic status, living environment, lifestyle, and health management, are the variables that have the greatest impact on the health of rural older adults. As a result, providing more precise health interventions with the characteristics of factors influencing health is a crucial guarantee for preserving and improving the health of rural older adults in China.

A data-driven method for modeling human factors in maritime accidents by integrating DEMATEL and FCM based on HFACS: A case of ship collisions

A data-driven method is proposed to measure the static and dynamic interrelations between human factors contributing to maritime accidents. The proposed method integrates the superiorities of the HFACS (Human Factors Analysis and Classification System), DEMATEL (Decision-Making Trial and Evaluation Laboratory), and FCM (Fuzzy Cognitive Map). First, a maritime accident scenario is defined based on 240 ship collision accident reports, then the human factors at different levels are identified and structured within the HFACS framework under the guidance of grounded theory. Second, the DEMATEL method is adopted to determine the causal relationship between human factors and the importance ranking of each factor based on historical accident statistics. The FCM model is developed in the end to realize dynamic prediction and diagnostic inference of human factors involved in maritime accidents. More objective and realistic results are presented by applying the proposed method without the necessity of expert judgment. The results show that “Lookout negligence”, “Poor safety management practice of the shipping company”, and “Failure to take effective collision avoidance actions promptly” are the top three important human factors, additionally, “Not familiar with COLREG” has the highest influencing degree and “Lookout negligence” has the highest influenced degree in the human factors network.

Business processes monitoring based on fuzzy cognitive maps

The subject matter of the article is a toolkit and monitoring processes of weakly structured business processes using fuzzy cognitive maps (FCMs). The goal is to create a model for monitoring and forecasting the course of business processes based on the FCMs, which provide flexibility and the ability to adapt to the conditions of changing circumstances in the process to be monitored, as well as insurance of the possibility of applying unstable FCM.s The task is to develop a formal monitoring system model; develop a computational FCM model; develop a method of using unstable FCMs: to develop a method for creating and using an FCM model. The methods used are graph modeling methods and computational experiment methods. The following results were obtained. A formal model of the system of monitoring and coordination of decisions regarding the course of business processes has been developed. A model of a weighted semantic graph was developed, which includes three types of vertices, namely, input vertices that will receive subjective evaluations of users regarding the course of the process, intermediate vertices that correspond to factors important from the perspective of the decision-maker, and final vertices that reflect integral evaluations of the quality of business process execution. A computational FCM model has been developed, which can adapt to the specifics of business logic due to the flexible adjustment of memory parameters and connections between FCM nodes. A method of using unstable FCMs has been developed. A methodology for creating and using FCMs designed for monitoring weakly structured business processes has been developed. Conclusions. The scientific novelty of the work is as follows: the model for monitoring and forecasting the course of business processes due to the use of a fuzzy cognitive map, in which the parameters of the importance and node memory and connections provide additional flexibility and the possibility of coordination and adaptation in the conditions of changing circumstances in the process to be monitored has been improved; a method of using unstable FCMs by setting limits on the values of the nodes excitation and using as a measure of excitation not only stable excitation values of FCM nodes but also the rate of growth of excitation values as an indicator of trends, which allows monitoring and forecasting the course of business processes has been proposed.

FCMpy: a python module for constructing and analyzing fuzzy cognitive maps

FCMpy is an open-source Python module for building and analyzing Fuzzy Cognitive Maps (FCMs). The module provides tools for end-to-end projects involving FCMs. It is able to derive fuzzy causal weights from qualitative data or simulating the system behavior. Additionally, it includes machine learning algorithms (e.g., Nonlinear Hebbian Learning, Active Hebbian Learning, Genetic Algorithms, and Deterministic Learning) to adjust the FCM causal weight matrix and to solve classification problems. Finally, users can easily implement scenario analysis by simulating hypothetical interventions (i.e., analyzing what-if scenarios). FCMpy is the first open-source module that contains all the functionalities necessary for FCM oriented projects. This work aims to enable researchers from different areas, such as psychology, cognitive science, or engineering, to easily and efficiently develop and test their FCM models without the need for extensive programming knowledge.

Randomized high order fuzzy cognitive maps as reservoir computing models: A first introduction and applications

Fuzzy Cognitive Maps (FCMs) have emerged as an interpretable signed weighted digraph method consisting of nodes (concepts) and weights which represent the dependencies among the concepts. Although FCMs have attained considerable achievements in various time series prediction applications, designing an FCM model with time-efficient training method is still an open challenge. Thus, this paper introduces a novel univariate time series forecasting technique, which is composed of a group of randomized high order FCM models labeled R-HFCM. The novelty of the proposed R-HFCM model is relevant to merging the concepts of FCM and Echo State Network (ESN) as an efficient and particular family of Reservoir Computing (RC) models, where the least squares algorithm is applied to train the model. From another perspective, the structure of R-HFCM consists of the input layer, reservoir layer, and output layer in which only the output layer is trainable while the weights of each sub-reservoir components are selected randomly and kept constant during the training process. As case studies, in this paper we consider solar energy forecasting with public data for Brazilian solar stations, hourly electric load of the power supply company of the city of Johor in Malaysia, solar energy dataset from United States National Renewable Energy Laboratory (NREL), electric load data from the Global Energy Forecasting Competition 2012 (GEFCom 2012), and PJM hourly energy consumption data. The experiments also include the effect of the map size, activation function, the number of order and the size of the reservoir on the accuracy of R-HFCM method. The obtained results confirm the outperformance of the proposed R-HFCM model in comparison to the other methods. This study provides evidence that FCM can be a new way to implement a reservoir of dynamics in time series modeling. The Python code of the model is publicly available for research replication.

How to Promote Urban Intelligent Transportation: A Fuzzy Cognitive Map Study.

As an important part of smart city, intelligent transportation is an critical breakthrough to solve urban traffic congestion, build an integrated transportation system, realize the intelligence of traffic infrastructure and promote sustainable development of traffic. In order to investigate the construction of intelligent transportation in cities, 20 initial affecting variables were determined in this study based on literature analysis. A questionnaire collected from professionals in intelligent transportation was conducted, and a total of 188 valid responses were received. Then the potential grouping was revealed through exploratory factor analysis. Finally, a causal model containing seven concepts was established using the practical experience and knowledge of the experts. A root cause analysis method based on fuzzy cognitive map (FCM) was also proposed to simulate intelligent transportation construction (ITC). The results indicate:(1) The 20 variables can be divided into six dimensions: policy support (PS), traffic sector control (TSC), technical support (TS), communication foundation (CF), residents’ recognition (RR), and talent quality (TQ); and (2) In the FCM model, all six concept nodes (PS, TSC, TS, CF, RR, and TQ) have a significant positive correlation with the target concept node ITC. The rank of the six dimensions according to correlation strength is TS, CF, PS, TSC, RR, and TQ. The findings of this paper can help academics and practitioners understand the deep-seated determinants of urban intelligent transportation construction more comprehensively, and provide valuable suggestions for policy makers. And thus, the efficiency of intelligent transportation construction can be improved.

PREDICTION OF SEED PURITY AND VARIETY IDENTIFICATION USING IMAGE MINING TECHNIQUES

Seed is a little embryonic plant that can be used to introduce plant infections to new areas while also allowing them to survive from one cropping season to the next. Seed health is a well-known component in modern agricultural science for achieving the required plant population and yield. Seed-borne fungus are a major biotic constraint in seed production around the world. The detection of seed-borne pathogens by seed health testing is a crucial step in the treatment of crop diseases. Speed and accuracy are critical requirements for longterm economic growth, competitiveness, and sustainability in agricultural output. Because human judgements in identifying objects and situations are variable, subjective, and delayed, seed prediction activities are costly and unreliable. Machine vision technology provides a nondestructive, cost-effective, quick, and accurate option for automated procedures. Seed variety, seed type (country seed or hybrid seed), seed health, and purity prediction were the four basic processes. We began the first procedure by aligning the seed bodies in the same direction using a seed orientation approach. Then, to detect atypical physical seed samples, a quality screening procedure was used. Their physical characteristics, such as shape, colour, and texture, were retrieved to serve as data representations for the prediction. This research introduces a new fuzzy cognitive map (FCM) model based on deep learning neural networks that predicts seed purity tests using data from biological investigations. The relevant data features from the seed test are extracted by FCM, which then effectively initialises the deep neural networks. The Levenberg–Marquardt (LM) technique for deep neural networks was discovered to improve seed purity test prediction. Four statistical machine learning algorithms (BP-ANN, Multivariate regression, and FCMLM deep learning). Furthermore, we demonstrated an improvement in the system''''s overall performance in terms of data quality, including seed orientation and quality screening. In independent numerical testing, the correlation coefficient between predicted values and true values acquired from experiments reached 0.9.