Search

Copyright of Cybernetics & Systems Analysis / Kibernetiki i Sistemnyj Analiz is the property of V.M. Glushkov Institute of Cybernetics of NAS of Ukraine and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Construction labor productivity (CLP) is affected by various interconnected factors, such as crew motivation and working conditions. Improved CLP can benefit a construction project in many ways, such as a shortened project life cycle and lowering project cost. However, budget, time, and resource restrictions force companies to select and implement only a limited number of CLP improvement strategies. Therefore, a research gap exists regarding methods for supporting the selection of CLP improvement strategies for a given project by quantifying the impact of strategies on CLP with respect to interrelationships among CLP factors. This paper proposes a decision support model that integrates fuzzy multi-criteria decision making with fuzzy cognitive maps to prioritize CLP improvement strategies based on their impact on CLP, causal relationships among CLP factors, and project characteristics. The proposed model was applied to determine CLP improvement strategies for concrete-pouring activities in building projects as an illustrative example. This study contributes to the body of knowledge by providing a systematic approach for selecting appropriate CLP improvement strategies based on interrelationships among the factors affecting CLP and the impact of such strategies on CLP. The results are expected to support construction practitioners with identifying effective improvement strategies to enhance CLP in their projects.

Fuzzy-rough cognitive networks (FRCNs) are interpretable recurrent neural networks, primarily designed for solving classification problems. Their structure is simple and transparent, while the performance is comparable to the well-known black-box classifiers. Although there are many applications on fuzzy cognitive maps and recently for FRCNS, only a very limited number of studies discuss the theoretical issues of these models. In this paper, we examine the behaviour of FRCNs viewing them as discrete dynamical systems. It will be shown that their mathematical properties highly depend on the size of the network, i.e., there are structural differences between the long-term behaviour of FRCN models of different size, which may influence the performance of these modelling tools.

Delay is a common occurrence in the country's construction projects. Identifying delay factors in these projects and determining the influence of these factors is necessary to achieve the objectives of management. In this study, the effective delay factors on construction projects are identified by using previous studies, project documents and experts opinions. Since these factors affect on each other, the fuzzy cognitive map has drawn for effective factors and assessment factors or management objectives. Then, the effect of each factor on the assessment factors are evaluated by using hybrid learning algorithm and prioritization factors are done by using fuzzy data envelopment analysis. The results of the survey in West Azerbaijan province show that “supervision technical weaknesses for overcoming technical and executive workshop problems”, “inaccurate estimate of workload, required equipments and project time” and “the multiplicity of decision centers on the doing of projects” are the most important delay factors in construction projects

A novel design method for time series modeling and prediction with fuzzy cognitive maps (FCM) is proposed in this paper. The developed model exploits the least square method to learn the weight matrix of FCM derived from the given historical data of time series. A fuzzy c-means clustering algorithm is used to construct the concepts of the FCM. Compared with the traditional FCM, the least square fuzzy cognitive map (LSFCM) is a direct solution procedure without iterative calculations. LSFCM model is a straightforward, robust and rapid learning method, owing to its reliable and efficient. In addition, the structure of the LSFCM can be further optimized with refinements the position of the concepts for the higher prediction precision, in which the evolutionary optimization algorithm is used to find the optimal concepts. Withal, we discussed in detail the number of concepts and the parameters of activation function on the impact of FCM models. The publicly available time series data sets with different statistical characteristics coming from different areas are applied to evaluate the proposed modeling approach. The obtained results clearly show the effectiveness of the approach.

Various emergencies are happening frequently in recent years, causing great loss of life and property. Therefore, it has become imperative to improve emergency management. Considering that the performance of emergency management could be affected by many different factors, it is hard to improve all the factors under the condition of limited resources. One approach that works well is to optimize the key factors that affect emergency management. To this end, an integrated method based on fuzzy cognitive map (FCM) and Pearson's product-moment correlation coefficient is presented in this article to determine the critical risk factors in emergency management. First, the causal relationships between the risk factors influencing emergency management are determined according to expert opinions. To verify if the survey results from experts are reliable, an item-average correlation test based on Pearson's product-moment correlation coefficient is performed. Then, two scenarios are designed and the FCM method is utilized to identifying the critical risk factors of emergency management. Finally, five critical factors are figured out, and the efficiency of emergency management could be enhanced by optimizing these five factors. In addition, a comparative analysis is also conducted to validate the advantages of the proposed method. [ABSTRACT FROM AUTHOR]

Greenhouse gas emissions and air pollutants from ships contribute to climate change and poor local air quality. While at berth, the use of shore-side electricity as an alternative technique to generate electricity to ships can greatly reduce emissions and improve air quality. The container terminals of Djibouti accommodate a significant number of ship calls, but there is a lack of emissions mitigation measures. The purpose of this study is to identify the most critical barriers that hinder the deployment of shore power supply in the container terminals of Djibouti. To achieve this aim, this study consults professional experts and experienced managers working in the maritime industry. The data collection is based on a survey questionnaire collected in the form of linguistic preferences to handle fuzziness of human perceptions. The collected linguistic preferences are later converted into quantitative data and analyzed using fuzzy cognitive map approach. The results reveal that power requirement, investment cost and electricity cost are the key barriers that currently influence the implementation of the shore power technology in Djibouti. The findings of the study have great implications and are hoped to assist decision makers and port authority in prioritizing the different barriers according to their importance, in an effort to accelerate the introduction and the development of green port strategies. [ABSTRACT FROM AUTHOR]

The local community is a complex socio-economic system, and its ability to function for an indefinitely long period of time (viability) is not investigated sufficiently today. The purpose of the research was, using the cognitive mapping, propose to the local community management developing their own management strategies to ensure its viability. Considering the weakly structured subject area of resource management for the viability of the local community and the complex dynamic nature of socio-economic processes, fuzzy cognitive reflection was suggested as a tool that provides opportunities for modeling the inherent complexity and uncertainty associated with socio-economic systems. This research shows a system of relations between concepts in the form of a causative network – a cognitive map of the resource management of a local community and proposes scales for measuring the concepts. During the simulation experiments, managed, indirectly managed and unmanaged resources for the viability of a local community were defined. In modeling, own income per inhabitant has been chosen as the target concept and as an indicator of the potential of an independent choice of direction for the development of the local community with the view toward the construction of resource management scenarios for the local community’s viability. As a result of the simulation, there were proposed some strategies for the growth of ‘own income per inhabitant’ and some recommendations were given for building management scenarios within these strategies. [ABSTRACT FROM AUTHOR]

Emergency case reasoning is essential to emergency management. In this paper, we propose a novel emergency case reasoning method based on fuzzy cognitive map (FCM), to model the inherent causal relationships in emergency cases. Specifically, we first obtain emergency domain elements and mine their association rules, by leveraging natural language processing technology and FT-Growth dada mining algorithm. We then design an effective algorithm to learn causal knowledge links from the gathered association rules. Finally, we construct an FCM regarding emergency events and show the reasoning process. Experiments on the gas explosion demonstrate that the proposed method can successfully model the internal causal relationships of emergency elements, and the development of the emergency event can be reflected by the reasoning process of the proposed method according to its varying variables of state. The proposed method can effectively inference and predict the tendency of emergency cases based on the reasoning process, which can further provide valuable decision supports to emergency responders. [ABSTRACT FROM AUTHOR]

Depletion of energy and environment pollution problems are the unprecedented challenges faced by the conventional chemical industry in China. The ever-growing awareness of energy and environment protection makes sustainable development increasingly play the crucial role in China's chemical industry. Most existing methods about chemical industry evaluation are economic-oriented, which neglect the environmental and social issues, especially conflicts among them. This paper develops a novel hybrid multiple criteria decision making framework under bipolar linguistic fuzzy environment based on VIKOR and fuzzy cognitive map to evaluate sustainable chemical industry. The new method captures the characteristics of uncertainty, inconsistency and complexity in the evaluation process of sustainable chemical industry. Meanwhile, combination of fuzzy cognitive map technique makes the new method consider not only the importance but also the interrelations about criteria and obtain better insight into sustainable chemical industry evaluation. A case study and comparison analysis with existing methods reflect the new proposed framework is more suitable to the needs of environment and energy protection in the sustainable chemical industry. [ABSTRACT FROM AUTHOR]

Accurate prediction of social logistics demands is essential to government5s policy formulation for the logistics industry as well as to enterprise's logistics activity planning. In this paper, a logistics demand prediction model construction method based on the fuzzy cognitive map (FCM) is proposed. This method comprehensively considers the mutual influence between five economic elements (GDP, total import and export volume, etc.) and logistics demands, and acquires the mutual influence weight through machine learning of historical data. Finally, a logistics demand prediction model is built, which can realize accurate prediction of the future logistics demands. The experimental results provide solid evidence for high precision and favorable performance of the model in predicting logistics demands. [ABSTRACT FROM AUTHOR]

Abstract The fuzzy cognitive map (FCM) is an effective tool for modeling dynamic decision support systems. It describes the analyzed phenomenon in the form of key concepts and the causal connections between them. The main aspects of the building of the FCM model are: concepts selection, determining the output concepts, criterion selection, and determining the relationships between concepts. It is usually based on expert knowledge. The main goal of the paper is to define the optimal in some sense FCM structure through the introduction of the notion of output concepts and minimizing the number of concepts and connections between them. The proposed approach allows for: (1) the selection of key concepts based on graph theory metrics and determining the connections between them; (2) the determination of the criterion of learning based on output concepts and fitting the learning process to the analyzed problem. A simulation analysis was done with the use of synthetic and real-life data. Experiments confirm that the proposed approach improves the learning process compared to the standard approaches. [ABSTRACT FROM AUTHOR]

Abstract In order to mitigate climate change and reduce fossil fuel dependency in Iran, the government of the country has announced its renewable energy policies to increase the use of renewable energies, but the share of the energy generation mix of Iran is very low due to the lack of public acceptance. These challenges continue and can be hard to overcome at all levels. This paper investigates this problem at regional level by measuring public acceptance towards development of climate-friendly technologies in order to provide required feedbacks to policy-makers of the government for ushering changes in their policies already made or in their executing mechanism, possibly deducting future risks such as public opposition from their end and improving the level of acceptance. This study uses a mixed-methods analytical approach for quantitatively taking that level, including creativity techniques and fuzzy cognitive maps (FCMs). FCMs could directly map out policy-makers' cognitions on the problem. This study provides the mathematical formulation of the problem with its conceptual interpretation to import policy-makers' knowledge into FCMs when the knowledge is gained explicitly with creativity techniques. The authors focused on a case of Solar Water Heater adoption in the city of Behbahan in Khuzestan Province. Graphical abstract Image Highlights • A combinative method for measuring public acceptance of clean energy technologies is proposed. • It provides the mathematical formulation of the acceptance problem with its conceptual interpretation. • It focused on a case study of solar water heater adoption in Iran. [ABSTRACT FROM AUTHOR]

Because the financial crisis early warning and monitoring is too complex, most of the current implementation can only alternately choose early warning in accordance with the criteria of monitoring the financial crisis. As a result, the security measures are not in accordance with the actual situation of the system, and cannot be adjusted quickly according to the changes of the system. This paper presents a financial crisis early warning detection algorithm based on fuzzy cognitive map. The relationship between financial data is obtained by fuzzy cognitive map, and the system crisis value is calculated by fuzzy cognitive map reasoning process. Finally, through the financial data of listed companies, the early warning and monitoring effect of the algorithm is verified. The experimental results show that the method is efficient, cost-effective, and can timely and reasonably reflect the crisis state of financial data. [ABSTRACT FROM AUTHOR]

Abstract Developing a comprehensive explanation of complex social phenomena is a difficult task that analysts often have to perform using vast collections of text documents. On the one hand, solutions exist to assist analysts in creating causal maps from text documents, but these can only articulate the relationships at work in a problem. On the other hand, Fuzzy Cognitive Maps (FCMs) can articulate these relationships and perform simulations, but no environment exists to help analysts in iteratively developing FCMs from text. In this paper, we detail the design and implementation of the first tool that allows analysts to develop FCMs from text collections, using interactive visualizations. We make three contributions: (i) we combine text mining and FCMs, (ii) we implement the first visual analytics environment built on FCMs, and (iii) we promote a strong feedback loop between interactive data exploration and model building. We provide two case studies exemplifying how to create a model from the ground-up or improve an existing one. Limitations include the increase in display complexity when working with large collection of files, and the reliance on KL-divergence for ad-hoc retrieval. Several improvements are discussed to further support analysts in creating high-quality models through interactive visualizations. Highlights • A new approach to combine Fuzzy Cognitive Mapping and Text Mining is proposed. • The approach allows to use qualitative evidence to quickly create mental models. • Design choices are highlighted and contrasted with related visual environments. • The approach is exemplified on two case studies with real-world data. [ABSTRACT FROM AUTHOR]

This study evaluates and analyzes the impacts of resilience engineering (RE) principles on integrated health, safety, environment, and ergonomics (HSEE) management system. In decision sciences, information should be reliable due to uncertainty and vagueness existing in information. To this end, in this study, the concept of Z‐numbers with fuzzy cognitive map (FCM) approach is integrated and a novel approach named Z‐number cognitive map is proposed. The main advantages of the proposed approach are determination of the weighted causality relations (for employing FCM) as well as handling uncertainty (for considering Z‐numbers concept). This approach is used to show the effects of RE indicators on HSEE management system. The required data for the proposed approach is collected from a large petrochemical plant by distributing questionnaires. According to the results, the RE principles have significant impact on HSEE management system. Top management commitment, learning, preparedness and awareness have the most impacts on environment, health, ergonomics and safety factors, respectively. This is the first study that employs Z‐number cognitive map for evaluating and improving the impacts of RE on HSEE factors in a large petrochemical plant. The proposed approach in this study, can help managers of various safety‐critical systems to improve their performance in terms of HSEE factors using RE concept. [ABSTRACT FROM AUTHOR]

Abstract The amount of food wastage produced at the global level generates high environmental, economic and social costs, such as greenhouse gas emissions, soil degradation, waste generation, consumption of natural resources, as well as economic losses, inequality and poverty. Taking stock of these problems, this paper conducts an empirical investigation in order to identify and recommend the most effective policy actions and private initiatives that might modify the current unsustainable food consumption model, characterizing high income countries, in order to achieve a significant reduction in the amount of food wastage. Specifically, it performs a fuzzy inference simulation by means of a three-step methodology: analyzing the use of language within the food waste reduction/valorization debate to identify system variables; deducing the map of causal-effect relationships among the identified system variables through interviews to a pool of experts; and finally, performing a fuzzy inference simulation, to identify drivers potentially able to discourage current unsustainable consumer behaviors. Among other things, the fuzzy analysis shows how some policy drivers, as "Public food waste rules", "Investments and infrastructure" and "Small-scale farming" are particularly effective in supporting a new and sustainable food consumption model. At the same time, the experts' knowledge allows highlighting the crucial role of "biorefinery" in fostering a transition towards a sustainable consumption model. This is an interesting result, as it points at the ability of biorefineries to enhance a general positive attitude of consumers which, in turn, would translate into more sustainable consumption practices. Highlights • Effective policy drivers and private initiatives to reduce the amount of food waste are identified. • Food waste system variables are elicited by means of discourse analysis. • Fuzzy inference is employed to investigate the causal-effect map derived from experts' knowledge. • Side-effects should be considered in designing policy interventions. [ABSTRACT FROM AUTHOR]

The study of drilling and blasting processes in excavation projects, especially in Iran, demonstrates various challenges and problems that eventually affect the technical and economic aspects of project performance. This paper introduces a methodology based on a computer-based fuzzy cognitive map approach to find and prioritize the problematic drilling and blasting factors in tunneling projects‏ in Iran. A particular cognitive map of the problem was designed by use of 34 problematic factors that selected by tunneling engineers in Iran. In the designed map, the weights of the problematic factors and their interactions were considered on the basis of the opinions of engineers. The designed map was finally solved by considering the causes and effects of the problematic factors. Results indicated that the most critical factors were respectively identified as the disregard for geomechanical changes, the lack of accurate drilling supervision and management, and the insufficient knowledge of blasting teams. [ABSTRACT FROM AUTHOR]

Objective: Tumors at any stage may progress into cancer. Till now, cancer classification is a challenging task for the researchers. Research on the cancer biology starts with the changes in the tissues. Oral cancer is a malignant cell growth in the oral cavity. Method: The proposed work combines Fuzzy Cognitive map (FCM) with Support Vector Machine (SVM) for grading oral tumor. The histological features are used as concepts and the interrelationships between the concepts are identified. FCM acts as a classifier to distinguish between benign and malignant cases. Further, the extracted output from FCM is fed as an input to the Support Vector Machine (SVM) classifier. This will improve the prediction capabilities. Result: The classification accuracy obtained for the proposed model is 92.10% for malignant cases and 94.11% for benign cases. Conclusion: The experimental results show that the combination of FCM with SVM obtained a good result when compared to the hybrid model using FCM. [ABSTRACT FROM AUTHOR]

The prevalence of big data is starting to spread across the public and private sectors however, an impediment to its widespread adoption orientates around a lack of appropriate big data analytics (BDA) and resulting skills to exploit the full potential of big data availability. In this paper, we propose a novel BDA to contribute towards this void, using a fuzzy cognitive map (FCM) approach that will enhance decision-making thus prioritising IT service procurement in the public sector. This is achieved through the development of decision models that capture the strengths of both data analytics and the established intuitive qualitative approach. By taking advantages of both data analytics and FCM, the proposed approach captures the strength of data-driven decision-making and intuitive model-driven decision modelling. This approach is then validated through a decision-making case regarding IT service procurement in public sector, which is the fundamental step of IT infrastructure supply for publics in a regional government in the Russia federation. The analysis result for the given decision-making problem is then evaluated by decision makers and e-government expertise to confirm the applicability of the proposed BDA. In doing so, demonstrating the value of this approach in contributing towards robust public decision-making regarding IT service procurement. [ABSTRACT FROM AUTHOR]

High-risk emergency systems are emerging as a new generation technology to prevent disasters. Latest research points out that these systems could protect properties and lives in an efficient way. Limited to the sources, the feasible way to improve the performance of the system is to identify critical success factors (CSFs) and then optimize them. In this paper, a multi-criteria decision-making (MCDM) approach integrating Affinity Diagram, Decision Making Trial and Evaluation Laboratory (DEMATEL), fuzzy cognitive map (FCM) and Dempster-Shafer evidence theory (evidence theory) is proposed to identify critical success factors in high-risk emergency system. The DEMATEL and FCM are initially combined to tackle the decision-making problem in theory and practice. This model has ability to fuse technical, economic, political and social attributes. The proposed method is applied to select CSFs for Chongqing city. [ABSTRACT FROM AUTHOR]

In recent years, the waste management field has received substantial attention from policymakers, organizations, academics, and researchers due to increased focus on sustainability and carbon footprint reduction as well as concerns around rapid depletion of natural resources, public health, and environmental impact. Studies on food waste management have become especially important given the dramatic growth of the world's population and global hunger and malnutrition crisis. Considering the fact that one-third of the world's food supply is wasted or lost annually while hundreds of millions of people are living with food insecurity, it is easy to understand the importance of research studying appropriate food waste management actions for sustainability. Since the subject of food waste involves complicated linkages, the determination of a suitable model is pivotal. Integrated assessment models (IAMs) have been commonly used to uncover hidden patterns and present insights to policymakers. Furthermore, these models are well-designed to integrate data, information, and multidisciplinary knowledge into a single framework. This project presents a Fuzzy Cognitive Map (FCM) extended with intuitionistic fuzzy sets using the documentary coding method. This intuitionistic FCM (iFCM) is used to analyze the primary factors, explore the interactions between food waste factors, and prioritize some policies to reduce food waste by incorporating hesitancy weight factors representing the lack of information. Then several what-if scenario analyses are generated to review the interrelationships between factors in the developed model and facilitate a decision-making process for researchers. Eventually, it is concluded that food waste reduction is achievable with the implementation of the right policies, and this also improves the other concepts such as the intention not to food waste, shopping routines, and planning routines. [ABSTRACT FROM AUTHOR]

In article the method, allowing to analyze risks of decrease in quality of professional training on the basis of the developed cognitive map (the weighed oriented graph of concepts and relations between them), formalizing expert estimates is offered. Realization of the offered method within information-analytical system of monitoring of quality as subsystem of the general information system of educational institution is described.

This paper aims to model an individual’s decision-making process in relation to macroeconomic dynamics that involve a large number of variables, which might inflict dimensionality issue in empirical analysis. We employ the fuzzy cognitive map (FCM) for this purpose, and present a parsimonious approach in assessing the impacts of uncertainty shocks on individual households by constructing FCM where households adjust their consumption and working hours in response to changes in exogenous economic uncertainty. We employ FCM to analyze how uncertainty shocks affect the households’ consumption, working hours, and income sources. We further conduct simulations to examine roles of expansionary fiscal policy in alleviating the negative impacts of uncertainty shocks. Our simulations yield similar results as compared to the existing literature on the impacts of uncertainty shocks. We suggest a hybrid algorithm of constructing FCM, and hence demonstrate the extensibility of FCM in analyzing complex macroeconomic systems.

The evolution of the Internet of Things is significantly affected by legal restrictions imposed for personal data handling, such as the European General Data Protection Regulation (GDPR). The main purpose of this regulation is to provide people in the digital age greater control over their personal data, with their freely given, specific, informed and unambiguous consent to collect and process the data concerning them. ADVOCATE is an advanced framework that fully complies with the requirements of GDPR, which, with the extensive use of blockchain and artificial intelligence technologies, aims to provide an environment that will support users in maintaining control of their personal data in the IoT ecosystem. This paper proposes and presents the Intelligent Policies Analysis Mechanism (IPAM) of the ADVOCATE framework, which, in an intelligent and fully automated manner, can identify conflicting rules or consents of the user, which may lead to the collection of personal data that can be used for profiling. In order to clearly identify and implement IPAM, the problem of recording user data from smart entertainment devices using Fuzzy Cognitive Maps (FCMs) was simulated. FCMs are an intelligent decision-making system that simulates the processes of a complex system, modeling the correlation base, knowing the behavioral and balance specialists of the system. Respectively, identifying conflicting rules that can lead to a profile, training is done using Extreme Learning Machines (ELMs), which are highly efficient neural systems of small and flexible architecture that can work optimally in complex environments.