No full-text available
To read the full-text of this research,
you can request a copy directly from the author.
... Logic plays a great part here, and classical expert systems are a well known example. On the other hand, in the 'connectionistic' approach, the representation of knowledge is numerical, where the weight values between the interconnected neurons (see below) represent knowledge in a distributed and generally unstructured way [54]. In this case, calculus and probability theory are important tools. ...
... Nowadays, the symbolic as well as the connectionistic camps have run up against certain barriers of their approach and seem more prepared to merge and also to integrate with other promising areas like genetic algorithms [36,56] and fuzzy systems [54]. In a recent textbook [32], this tendency of integration is extensively described and illuminated with examples. ...
... The theory of dynamic systems [8,54] refers to the analysis of systems in the course of time. Here, we confine ourselves to systems which are described by a set of differential or, respectively, a set of difference equationṡ ...
This PhD-thesis refers to an analysis of various models of recurrent artificial neural networks (especially of various generalized Hopfield networks) and to how they may be applied in order to solve certain optimization problems.
It concerns a recompiled version of my 1996 PhD-thesis in which certain typesetting errors have been repaired using modern TeX-tools.
... An AM model designed for storing and recalling fuzzy sets on a finite universe of discourse is called fuzzy associative memory (FAM) [19]. On the one hand, fuzzy sets can be interpreted as elements from a complete lattice [20]. ...
... A morphological neural network is equipped with neurons that perform an elementary operation from mathematical morphology, possibly followed by a non-linear activation function [23]. The class of FMAMs includes, for example, the max-minimum and max-product FAMs of Kosko [19], the max-min FAM of Junbo et al. [24], the max-min FAM with a threshold of Liu [25], the fuzzy logical bidirectional associative memories of Belohlavek [26], and the implicative fuzzy associative memories (IFAMs) of Sussner and Valle [9]. ...
... , a n ] T ∈ [0, 1] n , where a i = µ A (x i ) for all i = 1, . . . , n [19]. In this paper, we focus only on fuzzy sets defined in finite universes of discourse. ...
Max-C and min-D projection auto-associative fuzzy morphological memories (max-C and min-D PAFMMs) are two-layer feedforward fuzzy morphological neural networks designed to store and retrieve finite fuzzy sets. This paper addresses the main features of these auto-associative memories: unlimited absolute storage capacity, fast retrieval of stored items, few spurious memories, and excellent tolerance to either dilative or erosive noise. Particular attention is given to the so-called Zadeh’ PAFMM, which exhibits the most significant noise tolerance among the max-C and min-D PAFMMs besides performing no floating-point arithmetic operations. Computational experiments reveal that Zadeh’s max-C PFAMM, combined with a noise masking strategy, yields a fast and robust classifier with a strong potential for face recognition tasks.
... Amid the growing concern over the black-box nature of AI models, researchers have explored alternative techniques that offer boosted interpretability. Fuzzy Cognitive Maps [10,11], an established method in the realm of soft computing, have emerged as a promising paradigm to address the challenge of explainability in ML and DL applications. FCMs are graph-based models that excel in capturing complex causal relationships in a dynamic system [11]. ...
... Fuzzy Cognitive Maps [10,11], an established method in the realm of soft computing, have emerged as a promising paradigm to address the challenge of explainability in ML and DL applications. FCMs are graph-based models that excel in capturing complex causal relationships in a dynamic system [11]. Comprising a collection of interconnected concepts represented as nodes, FCMs leverage fuzzy logic to model imprecise relationships between these concepts [10,11]. ...
... FCMs are graph-based models that excel in capturing complex causal relationships in a dynamic system [11]. Comprising a collection of interconnected concepts represented as nodes, FCMs leverage fuzzy logic to model imprecise relationships between these concepts [10,11]. The strengths and directions of connections, represented by weighted edges, enable the representation of expert knowledge and domain expertise, making FCMs particularly suitable for medical applications [12][13][14]. ...
Myocardial Perfusion Imaging (MPI) has played a central role in the non-invasive identification of patients with Coronary Artery Disease (CAD). Clinical factors, such as recurrent diseases, predisposing factors, and diagnostic tests, also play a vital role. However, none of these factors offer a straightforward and reliable indication, making the diagnosis of CAD a non-trivial task for nuclear medicine experts. While Machine Learning (ML) and Deep Learning (DL) techniques have shown promise in this domain, their “black-box” nature remains a significant barrier to clinical adoption, a challenge that the existing literature has not yet fully addressed. This study introduces the Deep Fuzzy Cognitive Map (DeepFCM), a novel, transparent, and explainable model designed to diagnose CAD using imaging and clinical data. DeepFCM employs an inner Convolutional Neural Network (CNN) to classify MPI polar map images. The CNN’s prediction is combined with clinical data by the FCM-based classifier to reach an outcome regarding the presence of CAD. For the initialization of interconnections among DeepFCM concepts, expert knowledge is provided. Particle Swarm Optimization (PSO) is utilized to adjust the weight values to the correlated dataset and expert knowledge. The model’s key advantage lies in its explainability, provided through three main functionalities. First, DeepFCM integrates a Gradient Class Activation Mapping (Grad-CAM) algorithm to highlight significant regions on the polar maps. Second, DeepFCM discloses its internal weights and their impact on the diagnostic outcome. Third, the model employs the Generative Pre-trained Transformer (GPT) version 3.5 model to generate meaningful explanations for medical staff. Our dataset comprises 594 patients, who underwent invasive coronary angiography (ICA) at the department of Nuclear Medicine of the University Hospital of Patras in Greece. As far as the classification results are concerned, DeepFCM achieved an accuracy of 83.07%, a sensitivity of 86.21%, and a specificity of 79.99%. The explainability-enhancing methods were assessed by the medical experts on the authors’ team and are presented within. The proposed framework can have immediate application in daily routines and can also serve educational purposes.
... Starting from the problem of implementing artificial neural networks [5,6,8,9,13] for the automation of industrial processes, it was proposed to implement artificial neural structures based on programmable circuits [4,7,[10][11][12]. The problem of automating industrial processes is quite complex, and various alternative methods are used to solve it, including artificial intelligence. ...
... The hardware implementation of neural models requires the implementation of the architecture of the neuron based on programmable circuits. Since the basis of any neural network is the classical model of the neuron, the task is reduced to implementing its model in hardware [5,13]. In order to simplify the implementation process of the artificial neuron, the modular design of its internal architectures was realized [4,7]: inputs; synaptic weights; adder; activation function; outputs. ...
... An essential advantage of this architectural implementation method is the possibility of designing an entire system on a single circuit. The main advantage of implementing neural networks based on reconfigurable circuits can be fully exploited only in the case of using programmable circuits, a fact that offers the possibility of parallelizing the calculation processes carried out in the structure of each artificial neuron [5,13]. ...
In the process of transition to Industry 4.0, the importance of applying cutting-edge technologies such as machine learning and artificial intelligence to replace human operators in industrial processes is explained by the need to automate industrial production processes. Replacing qualified human experts with artificial neural networks opens up a lot of possibilities for the implementation of new methods of industrial process automation. The problem of industrial process automation is quite complex because the decision-making process of the human expert is accompanied by uncertainty. Artificial neural networks represent one of the basic branches of artificial intelligence. At the moment, they are used in various fields to solve problems for which classical methods are unable to provide practical solutions. Thus, the problem of developing and training artificial neural networks for solving industrial process automation problems acquires major importance in the design of artificial intelligence systems. The training process directly depends on the data set on the basis of which the neural network is designed.
... AND operation is functioned by multiplication of weights (w i ) of the related rules, such as Eq. 2; Normalization (N) Layer: It could be accepted as an early calculation of the average center of gravity in the defuzzification stage (Kosko, 1992). Total weight is used as a divisor of the related rule weight. ...
... where p i , q i , and r i are weighted parameters. This layer determines the position of the output MFs and implies (Kosko, 1992) the normalized impact degree of related rule ( w i ) to the output (Nguyen et al, 2003). O 4i refers to the weighted output of the ith rule in the 4th (Defuzzification) Layer (Eq. ...
... Aggregation Layer: If it is compared with classical FIS defuzzification formulas (Kosko, 1992), this layer could be accepted as the conclusion step of the Defuzzification Stage. The output vector of the previous layer is aggregated, and it yields a scalar output (Eq. ...
In residential real estate, location quality within the neighborhood has considered a very important characteristic. On account of a limited number of studies on novel evaluation methods in real estate literature, an Adaptive-Neuro-Fuzzy-Inference-System Grading Model (ANFISGM) which combines human knowledge-based FIS with optimization skills of ANN is proposed. By 4 location parameters, Distance to Open Space (DtOS), Parcel Size (PS), Excellence of View (EoV), and Distance to Parking (DtP), the model has been applied to grading the location quality of 27 detached properties within the campus region of Kocaeli University. Performance of the proposed model is compared with the Standard Grading Method (SGM), and Fuzzy Grading Model (FGM), which were developed considering the quality of property location (QoPL) within the neighborhood. In this study, the ANFIS model is proposed as the first contribution to the real estate valuations made in terms of location quality in the neighborhood. Since it was not very clear in previous studies, the individual and resultant effects of the parameters on the score are examined and interpreted by correlation surfaces. The lack of nonlinear interpolation, which reduces the sensitivity of traditional and fuzzy methods and causes them to assign the same value throughout the transition regions, is eliminated by the proposed ANFIS method. Hereby, ANFISGM declares an accurate and practical grading model to estimate the value of the residential real estate considering property location within the neighborhood. This paper expects that ANFISGM will contribute to the appraisal process within a minimum of detail and a limited period, especially for tax purposes.
... Our theoretical approach involves generalizing neuromorphism through the concept of a stochastic dynamic system (SDS). This approach has a rich history and has been applied in various fields, such as physics, mathematical physics, condensed-matter physics, optics, physical chemistry, biochemistry, economics, and information theory [21,34,35]. Dynamical systems have played a crucial role in the revival of ANN research since the early 1980s [13]. ...
... Even prior to that, they were recognized for their significance in neurodynamics, influencing both the neuroscience and machine intelligence communities from the 1940s to the 1980s and beyond, particularly in the early development of SNNs [18]. From the perspective of AI and machine learning, dynamical systems were proposed as a general approach to computational intelligence, particularly in connection with fuzzy logic and control [35]. In recent years, SDSs have also been suggested as a foundational framework for understanding how cognition arises in the neuronal circuits of the brain [22]. ...
This paper introduces a multidisciplinary conceptual perspective encompassing artificial intelligence (AI), artificial general intelligence (AGI), and cybernetics, framed within what we call the formalism of generalized neuromorphism. Drawing from recent advancements in computing, such as neuromorphic computing and spiking neural networks, as well as principles from the theory of open dynamical systems and stochastic classical and quantum dynamics, this formalism is tailored to model generic networks comprising abstract processing events. A pivotal aspect of our approach is the incorporation of the memory space and the intrinsic non-Markovian nature of the abstract generalized neuromorphic system. We envision future computations taking place within an expanded space (memory space) and leveraging memory states. Positioned at a high abstract level, generalized neuromorphism facilitates multidisciplinary applications across various approaches within the AI community.
... The second part of the paper concerns the application of triangular fuzzy numbers to medical diseases, more precisely in this case to kidney disease. Medical image segmentation based on fuzzy numbers [25], fuzzy modeling for medical image processing [21], behavioral neural networks on fuzzy systems [10] and triangular fuzzy numbers for medical image segmentation [22] are key elements of this paper, because the simulation of their application was done in MATLAB R O software. In the end, the analysis of the image was done and as an input it gives graphic fuzzy numbers that show the tendency of the value of the degree of redness, which represents an abnormality in the observed photographs (see Figure 2). ...
... Finally, we can use this central tendency value to classify the kidney image as normal or abnormal based on some predetermined criteria. For example, if the central tendency value is less than a certain threshold, we can classify the image as normal, otherwise, we can classify it as abnormal (see [1], [7], [8], [9], [10]). This is a simple example of how we can use fuzzy numbers and the center of gravity method to analyze and interpret medical images. ...
Fuzzy sets are a mathematical notion that allows us to represent uncertainty by assigning a degree of membership to a value in a range. This degree of membership represents the degree to which a particular value belongs to the fuzzy set. Fuzzy numbers are fuzzy sets that satisfy specific conditions, and can be applied in the interpretation of the behavior of neural networks. In many real-world problems, the output of a neural network may not be a precise numerical value, but rather a range of values that are subject to uncertainty. In the context of neu-ral networks, fuzzy numbers can be used to represent uncertainty in the output of the network. Fuzzy numbers are used in applications where the representation of ambiguity and uncertainty in numerical data is explicitly desired. This paper will consider discretizations and defuzzifi-cations triangular fuzzy numbers with the use of MATLAB software. MATLAB functions were applied to the analysis of kidney images, where the fuzzy numbers represent the tendency value of the degree of redness, which serves as an indicator for classifying the image as normal or abnormal based on different characteristics.
... Being a soft computing, powerful technique that combines the advantageous characteristics of both fuzzy logic and neural networks, FCM is particularly useful and suitable for modeling and decision-making for complex systems [18]. It is considered as an extension to Cognitive Maps (CM), introduced by Axelrod in 1976 to graphically represent the cognitive state of a system in the decision-making process. ...
... From the structural point of view, FCM can be graphically represented as a fuzzy digraph, which has the ability to explain the behavior of complex systems by integrating causal reasoning deriving from the perception of expert knowledge. The system is defined as a collection of concepts, interconnected to each other with connections in the form of directed edges, reflecting the cause-effect relationships between the concepts [18]. Essentially, FCM consists of two main components, the nodes and the edges. ...
Production line calibration is a critical industrial task that requires thoroughly planned actions. Even tiny deviations from the optimal settings can cause dramatic deficiencies. Automated Root Cause Analysis can be employed to suggest the actions that result in faulty states, and therefore, to resolve situations and prevent recurrence. This work presents a methodology for Root Cause Analysis focused on the calibration process of a valve block in an elevator system. The causalities (weighted interconnections) between oil flow control (actions) and system velocity (output) are estimated using Pearson Correlation. The produced weight matrix is evaluated by exploiting expert knowledge. An FCM model for Root Cause Analysis is developed to study the system behavior and explore the root causes of deficiencies. The proposed approach eliminates the need for labeled root causes. Results support the efficiency of the proposed FCM model for correcting the sub-optimal configurations; the proposed approach seems to work even when the calibration actions are unknown.KeywordsRoot Cause AnalysisFuzzy Cognitive MapsCorrelation CoefficientElevator Industry
... Fuzzy cognitive maps are a form of qualitative models developed in the social sciences and engineering (Kosko, 1992;Papageorgiou, 2011) which have an advantage over other qualitative models in that they allow for a relatively seamless merging of high-quality quantitative information with qualitative approximations of model parameters, including interaction strength (Clark-Wolf et al., 2022;Ramsey & Veltman, 2005;Roberts, 1986). These models are increasingly used for predicting outcomes of conservation actions, and referred to as FIWs (Ramsey & Veltman, 2005). ...
... ECOLOGY 5 of 13 partially assign membership using qualitative or linguistic values, according to the degree to which we are confident in a value using categories like "low," "medium" or "high" (Kosko, 1992). For example, we could be mostly confident that an interaction between two species is "high," so we assign much membership to that category. ...
The past 100 years of empirical research in ecology have generated tremendous knowledge about the component interactions that structure ecological communities. Yet, we still lack the ability to reassemble these puzzle pieces to predict community responses to perturbations, a challenge that grows increasingly urgent given rapid global change. We summarize key advances in community ecology that have set the stage for modeling ecological systems and briefly review the evolution of ecological modeling efforts to identify critical hurdles to progress. We find that while Robert May demonstrated that quantitative models could theoretically predict community interactions nearly 50 years ago, in practice, we still lack the ability to predict ecological outcomes with reasonable accuracy for three reasons: (1) quantitative models require precise data for parameterization (often unavailable) and have restrictive assumptions that are rarely met; (2) estimating interaction strengths for all network components is extremely challenging; and (3) determining which species are essential to include in models is difficult (model structure uncertainty). We propose that fuzzy interaction webs (FIW), borrowed from the social sciences, hold the potential to overcome these modeling shortfalls by integrating quantitative and qualitative data (e.g., categorical data, natural history information, expert opinion) for generating reasonably accurate qualitative predictions sufficient for addressing many ecological questions. We outline recent advances developed for addressing model structure uncertainty, and we present a case study to illustrate how FIWs can be applied for estimating community interaction strengths and predicting complex ecological outcomes in a multitrophic (plants, herbivores, predators), multi‐interaction‐type (competition, predation, facilitation, omnivory) grassland ecosystem. We argue that incorporating FIWs into ecological modeling could significantly advance empirical and theoretical ecology.
... The results are aggregated into categories of impact significance for every geographic entity. This is achieved through a fuzzy pattern classification algorithm (FPC) (Bojadziev and Bojadziev, 1995;Bojorquez-Tapia et al., 2009;Cox, 1994;Kosko, 1992;Miller, 1956;Terano et al., 1989;Wood et al., 2007). Computationally, FPC entails (1) categorization, (2) fuzzification, (3) inference, (4) combination, and (5) defuzzification (Appendix 1). ...
... Combination is the procedure by which fuzzy sets are aggregated to generate a fuzzy solution space. In our approach, we use a fuzzy additive system (Kosko, 1992) to combine the fuzzy sets that result from the interaction intensity and the environmental vulnerability indices. Defuzzyfication converts the fuzzy solution space to a crisp number. ...
The determination of impact significance is a critical step in Environmental Impact Assessment (EIA). Yet, the notion of impact significance is inherently subjective, immersed in uncertainty, and influenced by competing interests. This article addresses the difficult task of collaboratively determining the significance of the environmental impacts of projects in dispute. We introduce an approach centered on analytic deliberation that entails three steps: analysis, translation, and deliberation. Analysis combines and synthesizes impact significance into a single index using a fuzzy pattern classification algorithm, which also integrates the inherent uncertainty of impact assessment. Translation transforms the index into understandable and accessible spatial representations through geovisualization. Deliberation promotes safe spaces for collaboration in which stakeholders examine evidence openly and reflect on the conflicting values underlying their perspectives. The outcome of the approach is a compromise on the most meaningful representation of impact significance, if one exists, as the basis for agreement on the appropriate prevention, mitigation, and compensation measures of a project. Hence, it helps to reach agreement on the impact prevention, mitigation, and compensation strategy prior to the consultation process required by law in most countries. We illustrate our approach through an example from Mexico.
... The Bidirectional Associative Memory (BAM) type of neural network is another group of CNNs whose design is inspired by the associative phenomena existing in the human brain [34][35][36]. It extends the single-layer auto-associative correlation to two-layer heteroassociative circuits [37], which is essential in numerous applied problems [38][39][40]. ...
... Such NNs are composed of neurons arranged in two layers, the X-layer and Y-layer. A two-way associative search for stored bipolar vector pairs is performed by applying an iterative approach to the forward and backward information flows between the two layers [34][35][36][37][38]40,100]. ...
In recent years, cellular neural networks (CNNs) have become a popular apparatus for simulations in neuroscience, biology, medicine, computer sciences and engineering. In order to create more adequate models, researchers have considered memory effects, reaction–diffusion structures, impulsive perturbations, uncertain terms and fractional-order dynamics. The design, cellular aspects, functioning and behavioral aspects of such CNN models depend on efficient stability and control strategies. In many practical cases, the classical stability approaches are useless. Recently, in a series of papers, we have proposed several extended stability and control concepts that are more appropriate from the applied point of view. This paper is an overview of our main results and focuses on extended stability and control notions including practical stability, stability with respect to sets and manifolds and Lipschitz stability. We outline the recent progress in the stability and control methods and provide diverse mechanisms that can be used by the researchers in the field. The proposed stability techniques are presented through several types of impulsive and fractional-order CNN models. Examples are elaborated to demonstrate the feasibility of different technologies.
... Fuzzy logic applications in radiation treatment empower the exact calibration of radiation dosages, bookkeeping for tumor heterogeneity and spatial dispersion, hence protecting adjoining solid tissues [3]. ...
Fuzzy logic, characterized by its capacity to oversee imprecision and vulnerability, has found broad applications within the biomedical designing field. This report explains the noteworthy parts and commitments of Fuzzy logic in restorative diagnostics, treatment arranging, biomedical handling, and healthcare administration, supporting its potential to improve exactness and flexibility in biomedical arrangements.
... In the field of machine learning, particularly through fuzzy logic, has been instrumental in developing algorithms that can handle imprecise and vague data [43]. Fuzzy systems, with their capacity to handle linguistic variables and subjective human reasoning, have been applied extensively in pattern recognition, control systems, and prediction models [17]. ...
This bibliometric study aims to summarize the academic landscape of non-probabilistic data research, based on an examination of scientific output indexed in Web of Science and Scopus databases. It employs multiple methods to analyse and describe the collected corpus, including co-authorship and keyword co-occurrence networks to investigate patterns of collaboration and predominant research themes. Co-authorship analysis identified several robust research clusters, while keyword later spotlighted key thematic areas in the field. Countries, types of documents, categories, year of publication, citations and other metrics were also produced, and implications discussed. The findings present a structured overview of the non-probabilistic data research landscape, delineating the research trends, prominent authors, and emerging themes.
... Causal relationships between nodes are associated with a number or "weight" that determines the degree to which the dependent node relates to the incoming node. The weight (ei,j) between two nodes is usually normalized into the interval [-1,1], where -1 represents an entirely negative influence or effect, 0 means there is no causal relationship, and +1 stands for a wholly positive impact [28]. ...
This paper applies Fuzzy Cognitive Maps (FCMs) to understand the diverse behavior of municipal governments in Ecuador to find common elements that influence the well-being of citizens in the short and long term. Information gathering was conducted in two stages: in the first one, a group of 16 national experts was consulted to develop the initial FCM; in the second stage, local experts from 220 municipalities were interviewed to collect information on the general validity of initial FCMs and specific values given to concepts and relationships in their municipalities. Results show the importance of certain concepts for long-term municipal performance, such as the need for a competitive entrepreneurial sector, improving human resources in the municipality, and, particularly, having a competent mayor with leadership skills and a forward-looking vision that enables the development of municipal projects required to reach an efficient and equitable coverage of goods and services throughout the city. Through the application of genetic algorithms, the FCM was calibrated to ascertain the long-term dynamics of municipal development and the optimal values of the concepts that would optimize the attainment of the set objectives. The derived outcomes suggest the desirability of the maintenance of, in principle, unwanted structures like financial transfers from the central government and the need to exploit natural resources to attain urban development.
... Therefore, many reaction approaches have been introduced that allow the use of artificial intelligence techniques, including problem solving, learning, and reasoning. In this domain, fuzzy logic [5][6][7], neural networks [8][9][10] and other controlling techniques [11][12][13], have become the cornerstone of the navigation system in mobile robots. At stated in Pradhan et al. [14], a navigation approach for several mobile robots in an unknown environment using the fuzzy logic technique has been presented. ...
Mobile robots are increasingly used in service and industrial activities. For many previous decades, its navigation has always remained an open problem for researchers in the World. The target of this research is to develop a control method for mobile robots operating in dynamic and unknown environments with both static and moving obstacles. The method utilizes a fuzzy logic approach based on a Lidar sensor to gather information about the environment and make decisions for navigation. The study focuses on the use of mobile robots in material handling applications such as warehouses or libraries with flat floors. The results demonstrate the ability of the proposed method to navigate the mobile robot around both static and moving obstacles, enabling its use in various material handling applications. The study provides a potential solution for the open problem of mobile robot navigation in complex environments.
... Fuzzy systems represent an effective solution to manage the intrinsic uncertainty of data [70]. A fuzzy set represents an extension of the classical notion of a set, in which the concept of membership is binary, i.e., an element belongs or does not belong to the set. ...
Floods are among the most severe and impacting natural disasters. Their occurrence rate and intensity have been significantly increasing worldwide in the last years due to climate change and urbanization, bringing unprecedented effects on human lives and activities. Hence, providing a prompt response to flooding events is of crucial relevance for humanitarian, social and economic reasons. Satellite remote sensing using synthetic aperture radar (SAR) offers a great deal of support in facing flood events and mitigating their effects on a global scale. As opposed to multi-spectral sensors, SAR offers important advantages, as it enables Earth's surface imaging regardless of weather and sunlight illumination conditions. In the last decade, the increasing availability of SAR data, even at no cost, thanks to the efforts of international and national space agencies, has been deeply stimulating research activities in every Earth observation field, including flood mapping and monitoring, where advanced processing paradigms, e.g., fuzzy logic, machine learning, data fusion, have been applied, demonstrating their superiority with respect to traditional classification strategies. However, a fair assessment of the performance and reliability of flood mapping techniques is of key importance for an efficient disasters response and, hence, should be addressed carefully and on a quantitative basis trough synthetic quality metrics and high-quality reference data. To this end, the recent development of open SAR datasets specifically covering flood events with related ground-truth reference data can support thorough and objective validation as well as reproducibility of results. Notwithstanding, SAR-based flood monitoring still suffers from severe limitations, especially in vegetated and urban areas, where complex scattering mechanisms can impair an accurate extraction of water regions. All such aspects, including classification methodologies, SAR datasets, validation strategies, challenges and future perspectives for SAR-based flood mapping are described and discussed.
... This methodology facilitates the evaluation of how various variables impact business outcomes by enabling the exploration of "whatif " scenarios and the assessment of changes in input variables (AI and XAI metrics) and their effects on outputs (KPIs). The choice of FCMs for the validation framework has multiple advantages (Kosko, 1991): (a) Modeling Complexity: FCMs are ideal for complex systems with numerous interconnected variables and cause-effect relationships, facilitating the representation of intricate technical and business metric interactions. (These models can be obtained through various methods (Özesmi and Özesmi, 2004), including (1) questionnaires, (2) extraction from written texts, (3) drawing from data depicting causal relationships, or (4) direct creation through interviews with experts who construct them), (b) Quantitative Translation: FCMs quantitatively translate qualitative expert insights into numerical data, enabling simulations and KPI predictions, (c) Scenario Analysis: FCMs excel in scenario analysis, allowing researchers to explore variable impacts on KPIs, aiding decision-making and optimization, (d) Efficiency and Reproducibility: FCMs provide an efficient, reproducible method for evaluating AI system impact without repeated interviews or data collection and (e) Visual Clarity: FCMs offer visual representations of causal relationships, enhancing understanding for researchers and stakeholders. ...
Explainable Artificial Intelligence (XAI) has gained significant attention as a means to address the transparency and interpretability challenges posed by black box AI models. In the context of the manufacturing industry, where complex problems and decision-making processes are widespread, the XMANAI platform emerges as a solution to enable transparent and trustworthy collaboration between humans and machines. By leveraging advancements in XAI and catering the prompt collaboration between data scientists and domain experts, the platform enables the construction of interpretable AI models that offer high transparency without compromising performance. This paper introduces the approach to building the XMANAI platform and highlights its potential to resolve the “transparency paradox” of AI. The platform not only addresses technical challenges related to transparency but also caters to the specific needs of the manufacturing industry, including lifecycle management, security, and trusted sharing of AI assets. The paper provides an overview of the XMANAI platform main functionalities, addressing the challenges faced during the development and presenting the evaluation framework to measure the performance of the delivered XAI solutions. It also demonstrates the benefits of the XMANAI approach in achieving transparency in manufacturing decision-making, fostering trust and collaboration between humans and machines, improving operational efficiency, and optimizing business value.
... We are witnessing an increasing interest in these systems because of their great potential for solving complex problems and their numerous applications in engineering and other fields. All started by solving problems in optimization theory and quickly their use was spread to pattern recognition, system identification, parallel computing and many other fields [1][2][3][6][7][8][9][10][11]15,17]. ...
Of concern is a Cohen–Grossberg neural network ( CGNNs ) system taking into account distributed and discrete delays. The class of delay kernels ensuring exponential stability existing in the previous papers is enlarged to an extended class of functions guaranteeing more general types of stability. The exponential and polynomial (or power type) type stabilities becomes particular cases of our result. This is achieved using appropriate Lyapunov-type functionals and the characteristics of the considered class.
... Her bir ağ katmanlar şeklinde yapılanmıştır (Şekil 6). ANFIS yönteminde hem yapay sinir ağları (YSA) hem de bulanık mantık (BM) kullanılır (Kosko, 1992). ANFIS, YSA'nın öğrenme yeteneğini ve kuralları belirlerken bulanık mantığın çıkarım yöntemini kullanarak çıkış verisi üretmektedir (Uzunali, 2019). ...
Adaptive Network Based Fuzzy Logic Inference System (ANFIS); has been developed as a prediction model by using the learning ability of artificial neural networks (ANN) and the decision-making mechanism of fuzzy logic approach. Daily average discharges at two stream gages located in the Kızılırmak River is tried to be predicting with two different ANFIS models in this study. Daily average discharge of the river observed between 2014-2021 and daily total precipitation data of two Weather Stations (AWS) representing the river basins are used in the models. ANFIS models have been formed with 2 input and 1 output approach for SG-1 Stream Gage in the upstream, and with 3 input - 1 output approach for SG-2 Stream Gage which takes place at downstream. Total daily precipitation has two days lag time (t-2) and average daily discharge has one day lag time (t-1) taken as input data and (t) days as output. 75% of the data is used as training and 25% as test. While creating the rules, three different clusters have been made, and the membership function of the target value is obtained. Coefficient of determination (R2) and root mean square error (RMSE) metrics are used for the performance of the models. The best results for both SG-1and SG-2 are three clustered model with respectively, R2 = 0.9578 and 0.976, RMSE = 1.49 and 2.20. As a result, it was observed that the ANFIS model predicted the daily average discharge with high success.
... Her bir ağ katmanlar şeklinde yapılanmıştır (Şekil 6). ANFIS yönteminde hem yapay sinir ağları (YSA) hem de bulanık mantık (BM) kullanılır (Kosko, 1992). ANFIS, YSA'nın öğrenme yeteneğini ve kuralları belirlerken bulanık mantığın çıkarım yöntemini kullanarak çıkış verisi üretmektedir (Uzunali, 2019). ...
Akarsuların su potansiyelinin belirlenmesi için sezgisel tahmin modelleri sıklıkla kullanılmaktadır. Bu modellerden birisi olan Uyarlamalı Ağ Tabanlı Bulanık Mantık Çıkarım Sistemi (ing. kıs. ANFIS); yapay sinir ağlarının (YSA) öğrenme yeteneğini ve bulanık mantık (BM) yaklaşımının karar verme mekanizmasını kullanarak tahmin modeli geliştirmektedir. Bu çalışmada; Kızılırmak Nehri’nde yer alan iki adet Akım Gözlem İstasyonu’nda (AGİ) günlük ortalama debi, iki farklı ANFIS modeli ile tahmin edilmeye çalışılmıştır. AGİ’lere ait 2014-2021 yılları arasında gözlemlenmiş günlük ortalama debi verileri ile AGİ’lerin kurulu olduğu akarsu havzalarını temsil eden iki Meteoroloji Gözlem İstasyonu (MGİ)’ye ait günlük toplam yağış verileri mekansallaştırılarak modellerde kullanılmıştır. Membadaki Kızılırmak–Ahmethacı AGİ-1 için, 2 giriş 1 çıkış yaklaşımı, bu AGİ’nin mansabında kalan Kızılırmak–Bulakbaşı AGİ-2 için ise 3 giriş 1 çıkış yaklaşımı ile ANFIS modelleri kurgulanmıştır. Giriş verilerinden günlük toplam yağış, zaman ölçeğinde (t-2). gün, günlük ortalama debi, (t-1). gün alınmış ve çıkış olarak (t). güne ait ortalama debi tahmin edilmiştir. Modellerde verilerin %75’i eğitim, %25’i test verisi olarak kullanılmıştır. Kurallar oluşturulurken 3 farklı kümeleme yapılmış ve hedef değerin üyelik fonksiyonu belirlenmiştir. Her iki AGİ için eğitim ve test verilerinde 3 ayrı kümelemeye ait sonuçlar elde edilmiş ve modellerin başarımları için determinasyon katsayısı (R2) ve karekök ortalama hatası (RMSE) metrikleri kullanılmıştır. AGİ-1 için en iyi sonucu R2 = 0.9578, RMSE = 1.49 ile 3 kümelemeli model verirken AGİ-2 için en iyi sonucu; R2 = 0.976 ve RMSE = 2.20 ile yine 3 kümelemeli model vermiştir. Sonuç olarak ANFIS modeli, yüksek başarım ile günlük ortalama debiyi tahmin etmiştir.
... In the literature, GA, PSO, RNN and SVM are the commonly used AI models for combination with other AI models to obtain a more effective hybrid AI model with better performance, such as GA-SVR, GA-ANN, GA-FNN, PSO-RNN, PSO-SVM, PSO-ANN, ANN-GANN and SVM-SA [49]. Hybrid AI models have shown their great potential in solving new or difficult environmental problems related to sewage and are receiving increasing attention from researchers [50][51][52]. ...
In recent years, artificial intelligence (AI), as a rapidly developing and powerful tool to solve practical problems, has attracted much attention and has been widely used in various areas. Owing to their strong learning and accurate prediction abilities, all sorts of AI models have also been applied in wastewater treatment (WWT) to optimize the process, predict the efficiency and evaluate the performance, so as to explore more cost-effective solutions to WWT. In this review, we summarize and analyze various AI models and their applications in WWT. Specifically, we briefly introduce the commonly used AI models and their purposes, advantages and disadvantages, and comprehensively review the inputs, outputs, objectives and major findings of particular AI applications in water quality monitoring, laboratory-scale research and process design. Although AI models have gained great success in WWT-related fields, there are some challenges and limitations that hinder the widespread applications of AI models in real WWT, such as low interpretability, poor model reproducibility and big data demand, as well as a lack of physical significance, mechanism explanation, academic transparency and fair comparison. To overcome these hurdles and successfully apply AI models in WWT, we make recommendations and discuss the future directions of AI applications.
... AIDs patients, Dalits, Rag pickers, PWDs, etc. It is an exceptionally advantageous basic and useful asset, which is utilized in various fields, for example, social, prudent and clinical etc [9]. ...
Fuzzy Clustering is a type of bunching where every datum point can have a place with more than one group. In fuzzy clustering, the fuzzy c-means algorithm (FCM) is the most popular. k-means clustering intends to segment n perceptions into k clusters in which every perception has a place with the cluster with the closest mean. The point of this paper is to investigate the reasons for self-destruction and tackle the issue utilizing the strategy called triangular fuzzy clustering. Understudies for the most part endeavor suicides in light of mental wretchedness. Here we utilize triangular fuzzy clustering model to investigate the issue. In our review 50 self-destruction endeavor understudies' companions or guardians were met and their explanation were thought of and the triangular fuzzy clustering model was placed in to order the issue into low, medium and high. This paper comprises of four segments. Segment 1 gives the inception of the issue and furthermore the explanation of the model. Segment 2 gives the starting and the basics. Segment 3 give out the requesting of the model. Segment 4 gives the end and suggestion
... Some of the algorithms are commonly used in the literature (kNN [11,12], naive Bayes [13][14][15][16][17], majority vote [9,10,18]), while the remaining algorithms have been specifically developed by Semeion for pattern recognition. The objective was to compare the effectiveness and efficiency of the algorithms and determine which ones would yield the most accurate and reliable results: (a) backpropagation (Bp) [19][20][21]; (b) deep learning (Deep) [22][23][24]; (c) adaptive vector quantization (AVQ) [25][26][27][28]; (d) kNN [11,12]; (e) meta Bayes (Mb) [29]; (f) Conic Net [30]; (g) Sine Net (Sn) [31]; (h) bimodal (Bm) [32]; (i) majority vote (Mv) [9]; (j) naive Bayes [13][14][15][16][17]; (k) supervised contractive map (SVCm) [32]. The validation protocol used for all the algorithms is the training-testing protocol [33][34][35] (Figure 5: Validation protocol-5 × 2 CV (training-testing)). ...
The automatic identification system (AIS) facilitates the monitoring of ship movements and provides essential input parameters for traffic safety. Previous studies have employed AIS data to detect behavioral anomalies and classify vessel types using supervised and unsupervised algorithms, including deep learning techniques. The approach proposed in this work focuses on the recognition of vessel types through the “Take One Class at a Time” (TOCAT) classification strategy. This approach pivots on a collection of adaptive models rather than a single intricate algorithm. Using radar data, these models are trained by taking into account aspects such as identifiers, position, velocity, and heading. However, it purposefully excludes positional data to counteract the inconsistencies stemming from route variations and irregular sampling frequencies. Using the given data, we achieved a mean accuracy of 83% on a 6-class classification task.
... for the meaning of various terms used above one can refer [ 1] ,the term ( ) in (1) is the external stimulus to the neuron and has been taken as self-feedback x(t) is the argument of the function in(4). Hopfield model was derived by minimizing the energy(constraint) of neural networks so that self-loop is not permissible [3][4].Neuron takes feedback from other neurons but selffeedback is not observed [5] .Here we present Hopfield model of a neuron action given by a nonlinear integro-differential equation in two unknowns. ...
In this paper, we have presented Hopfield Model of a Neuron Dynamics under external stimulus. In this model we have taken a nonlinear integro-differential equation in the presence of external stimulus without any self-feedback. We have shown that the solution is bounded and not closed curve in Phase plane. Some conditions ensure the existence and uniqueness of equilibrium point that are derived. MSC2010: 92B20, 68T05, 82C32. 1. Introdution: Hopfield developed many applications in different areas such as pattern recognition model identification and optimization .These applications depend on the neural network dynamical behavior analysis of Hopfield neural network and these dynamical behaviors has important leading significance in the field of design application. 2. Neuron Dynamics: The neuronic equation considered by Caianiello and De Luca [2] is given by () 0 () ∫ () 1 (1) Above equation simplified by Gopalsamy and Leung [5-6] has the following assumptions () () () (2) , () ∫ () () , () ∫ () ()-(3)
... Te previously proposed systems are all single-layer associative memory neural networks; Kosko established a neural network with bidirectional associative memory in 1987, known as BAM neural network (BAMNN) [24][25][26]. Te BAMNN is diferent from the previously proposed systems in that the BAMNN model popularizes the common single-layer associative memory neural network to realize the mutual transmission of information between two-layer neurons [27]. Over the years, research studies on the BAMNN have yielded many results. ...
This paper introduces the stability problems of Cohen–Grossberg type BAM neural network (BAMCGNN) with piecewise constant argument (PCA). By employing the homeomorphism theory, sufficient conditions for the existence and uniqueness of the equilibrium point are obtained; using inequality technique and Lyapunov method, sufficient stability criteria for BAMCGNN with PCA are presented. Finally, a numerical case shows the significance of the results of this paper.
... The correspondence between neural network models and fuzzy systems has been first investigated by Kosko in his seminal work [71]. In his view, "at each instant the n-vector of neuronal outputs defines a fuzzy unit or a fit vector. ...
In this paper we investigate the relationships between a multipreferential semantics for defeasible reasoning in knowledge representation and a multilayer neural network model. Weighted knowledge bases for a simple description logic with typicality are considered under a (many-valued) ``concept-wise" multipreference semantics. The semantics is used to provide a preferential interpretation of MultiLayer Perceptrons (MLPs). A model checking and an entailment based approach are exploited in the verification of conditional properties of MLPs.
... The heavy FCCU process nonlinearities are further complicated by strong interchannel coupling, and requires a 'broad-based' rule-base, for robust control. Based on previous work by the author (P. Sarma and A. Ikonomopoulos, 1998;P. Sarma, 2000a) along with several other standard FLC references (C.C. Lee, 1990;B. Kosko, 1992;T. Asai et al, 1992), the heuristically common FLV fuzzy grid of N = 7 was used. Thus the square FRB of 7 × 7 = 49 rules (49-FRB), given in the left of Fig. 3 was used. The associated normalised nonlinear stabilising FLC input/output surface (FIOS) can be seen in on the right in Fig. 3 It indicates potentially good FLC closed-loop perfor ...
Fluid catalytic cracker units (FCCU's) are key modules of refineries. FCCU controller complexities arise from severe nonlinearities, strong coupling, multivariable systems, among others. Most FCCU controllers today are the linear model predictive control (LMPC) type. Shifts in operation modes, feedstock, or heavy disturbances can force time and effort-intensive LMPC re-validation/identification to capture the shifted linear dynamical model, caused by significant true FCCU nonlinearities. An intelligent control system (ICS), which is an explicitly nonlinear, greybox, multivariable controller is designed. The ICS features a relatively simple auto-tuning/identification setup. The ICS design has a chain of single channel fuzzy logic controllers (FLC's) as its basis. The scaling gain layer is augmented blockwise by an original sigmoidal gain-schedule. This gain-scheduled FLC (GS-FLC) combines with a simple fixed static linear decoupler (SLD). The GS-FLC is strongly related to a neurofuzzy network ICS, but with large parameter-data compression, and an intuitive design. GS-FLC auto-tuning was by an evolutionary algorithm (EA), and indicates practical viability. The EA provides globally optimal tuning. FCCU/GS-FLC robustness tests show excellent performance for the EA/GS-FLC/SLD providing for robust, dark grey-box, multivariable nonlinear control of the FCCU. The results are significantly superior to a sophisticated adaptive nonlinear MPC (ANMPC) controller for the identical FCCU process model. The EA/GS-FLC/SLD is leaner in structure and computation than the ANMPC, while demonstrating superior performance, and has a general intuitive design. It allows for wider ranges of FCCU operations, without the frequent re-tuning or re-identification necessary in LMPC. 2
... ANNs are emerging paradigms for solving complex problems in science and engineering [7][8][9][10]. The ANNs have the following features: (i) they mimic some simple behavior of a human brain; (ii) they have massively parallel architecture/topology; (iii) they can be represented by adaptive circuits with input channel, weights (parameters/ coefficients), one or two hidden layers, and output channel with some non-linearities; (iv) the weights can be tuned to obtain optimum performance of the neural network in modeling of a dynamic system or non-linear curve fitting; (v) they require training algorithms to determine the weights; (vi) they can have feedback-type arrangement within the neuronal structure leading to recurrent neural networks (RRNs); (vii) the trained network can be used for predicting the behavior of the dynamic system, and also for parameter estimation; (viii) they can be easily coded and validated using standard software procedures; (ix) optimally structured neural network architectures can be hard-wired and embedded into a chip for practical applications -this will be the generalization of the erstwhile analog circuits-cum-computers; and (x) then, the neural network-based system can be truly termed as a new generation powerful/ parallel computer. ...
Applications and concepts of fuzzy inference systems in wireless communications are reviewed to demonstrate their effectiveness in signal processing and telecommunications. We believe this to be the first such research. This study will first identify common fuzzy logic and fuzzy-hybrid methods for channel estimation, equalization, and decoding, and then describe the settings and scenarios where these approaches work well. This article breaks down how fuzzy logic can be used to solve real problems and then suggests practice-oriented research opportunities. This study focuses on the techniques of using fuzzy logic in the various fields of data communication, channel equalization, changeover management, and quality of service management. The comparison of proposed approaches has been done with LMS and RLS algorithms, and a significant improvement in the value of performance metrics has been achieved. Specifically, our proposed approach resulted in a 30% increase in signal-to-noise ratio (SNR) compared to LMS and RLS algorithms. These results demonstrate the effectiveness of fuzzy logic-based approaches in wireless communications, and suggest promising avenues for further research. Additionally, the book Advanced Heterogeneous Networks also focuses on the applications of fuzzy logic in the realm of communication systems.
Penelitian ini bertujuan untuk menghasilkan prototipe sistem kontrol yang dapat diterapkan pada sistem hibrid menggunakan sinar matahari dan gas LPG untuk menjaga kestabilan dan kelangsungan dengan metode logika fuzzy. Metode yang digunakan meliputi desain kolektor surya, pengantaran gas, desain sistem kontrol menggunakan metode logika fuzzy, uji fungsional, dan uji kinerja. Parameter yang diukur dalam uji pengering melibatkan suhu udara, kecepatan aliran udara, konsumsi energi gas LPG, dan pengurangan berat bahan. Hasil pengukuran digunakan untuk menghitung energi pengeringan, efisiensi pengering, dan kadar air. Dari observasi yang dilakukan pada sistem kontrol logika fuzzy, kadar air sagu berkurang dari 44,17%ww menjadi 6,52%ww setelah dikeringkan selama 4 jam pada suhu stabil 58 0C dengan konsumsi gas LPG sebanyak 0,37 kg. Sementara itu, dengan menggunakan energi surya, kadar air sagu berkurang dari 44,17% wt menjadi 5,69% wt setelah dikeringkan selama 10 jam. Penggunaan daya hibrida memungkinkan penghematan energi, overshoot kecil, dan suhu yang stabil.
This study tries to predict blast-induced flyrock using intelligent modelling techniques. Flyrock is a site-specific phenomenon. Design variables and rock properties highly influence flyrock throw distance. Site investigations were conducted in a sandstone quarry. Fundamental operational parameters, blast dimensions, bench face condition, and rock mass structure were monitored. Stepwise regression technique was applied for variable selection. Burden–hole diameter ratio, in situ block size, and powder factor were determined as the most significant parameters. Considering output of stepwise regression, artificial neural network, ANFIS, and Gaussian process regression techniques were applied to predict flyrock throw. A comprehensive validation was performed using twelve different performance indices. Pre-determination of input parameters supported development of successful soft computing applications. Rock block size was found to be an appropriate input variable for flyrock modelling. In addition to classical performance indices, standardized and symmetric accuracy metrics were quite useful in model validation process. The intelligent models predict flyrock range with an error less than 6 m. The mean percentage errors are lower than 10%. ANFIS seems to be the best model for flyrock prediction. The calculated mean absolute error is 5.36 for ANFIS model.
Of concern is the Hopfield neural network system comprising discrete as well as distributed delays in the form of a convolution. For a desired convergence rate of the solution to the equilibrium state, we establish sufficient conditions on the delay kernels ensuring this matter. Our result improves an existing one in the literature. The adopted approach is completely different. It relies on a judicious choice of a Lyapunov-like function and careful manipulations.
Aeroservoelasticity (ASE) extends the concept of aeroelasticity to address the aeroelastic interactions between aerodynamic forces and a flexible structure, which may include a control system. Then the classic Collar aeroelastic triangle can be extended to form the aeroservoelastic pyramid, where there are now forces resulting from the control system as well as the aerodynamic, elastic and inertial forces. Considerations of the aeroservoelastic interactions increase the importance of engineering efforts to incorporate lightweight and flexible structures, as well as high-gain digital flight control systems. Such considerations are important to account for aeroservoelastic instability. The dynamics of the guidance and control system may significantly affect aeroelastic problems, or vice versa, hence the term aeroservoelasticity. The FEM-based structural analysis is also essential for static aeroelastic studies in the nascent field of compliant blade performance modification. By way of introduction, mathematical modeling of a simple aeroelastic system with a control surface is elaborated. As a basic aeroservoelastic System that can shed some light on its state of affairs, the binary aeroelastic model will be helpful in analyzing flutter behavior as a baseline. Consideration is given to the effect of gusts. A particular case study on Aeroelastic Analysis of an Aircraft with Stand-By Actuator Using State-Space Approach is also presented for detailed treatment of the problem. Other examples discussed are the Design and Optimization of an Aeroservoelastic Wind Tunnel Model and Aeroservoelastic Modelling and Analysis of a Highly Flexible Flutter Demonstrator.KeywordsAeroelasticityAeroservoelasticityControls surfaceControl systemPhysical and mathematical modelingAircraft system modeling
Purpose
The paper’s main goal is to examine the relationship between the video marketing of financial technologies (Fintechs) and their vulnerable website customers’ brand engagement in the ongoing coronavirus disease 2019 (COVID-19) crisis.
Design/methodology/approach
To extract the required outcomes, the authors gathered data from the five biggest Fintech websites and YouTube channels, performed multiple linear regression models and developed a hybrid (agent-based and dynamic) model to assess the performance connection between their video marketing analytics and vulnerable website customers’ brand engagement.
Findings
It has been found that video marketing analytics of Fintechs’ YouTube channels are a decisive factor in impacting their vulnerable website customers’ brand engagement and awareness.
Research limitations/implications
By enhancing video marketing analytics of their YouTube channels, Fintechs can achieve greater levels of vulnerable website customers’ engagement and awareness. Higher levels of vulnerable customers’ brand engagement and awareness tend to decrease their vulnerability by enhancing their financial knowledge and confidence.
Practical implications
Fintechs should aim to increase the number of total videos on their YouTube channels and provide videos that promote their customers’ knowledge of their services to increase their brand engagement and awareness, thus reducing their vulnerability. Moreover, Fintechs should be aware not to over-post videos because they will be in an unfavorable position against their competitors.
Originality/value
This research offers valuable insights regarding the importance of video marketing strategies for Fintechs in promoting their vulnerable website customers’ brand awareness during crisis periods.
During the execution control of their initiatives, organisations use a variety of devices to aid independent direction. Regardless, they are still insufficient in the face of skewed statistics and shifting management approaches. The absence of frameworks for controlling the execution of enterprises has an impact on the nature of their categorization in terms of supporting independent direction. The presentation of soft registering methods, which provide heartiness, effectiveness and flexibility at apparatuses, is an optional arrangement. This research provides a technique for project execution control based on Soft Computing and ML, which contributes to the executives’ ability to further improve the project. The proposed method allows for AI and the replacement of fuzzy inference frameworks in project evaluation. The results are derived from seven calculations involving space apportioning, neural architecture, gradient descent and genetic algorithms. Adoption of the proposed framework, which has been included in this paper for project personnel, signifies a change in the nature of venture evaluation. The obtained result ensures that the apparatuses are in perfect working order to assist the independent direction in projecting the executive associations.
The economy of any nation is determined by the development of its industrial sectors. One of the most vibrant industries is leather industry. The process of it comprises of three stages among which tanning is the core action as it gives glow to the product. But, at the same time the material Chromium used for tanning indeed exploit the environment as it has toxic effects on all the organisms. The discharge of effluents contains Chromium (Cr) VI which is very hazardous; therefore the industries apply certain mechanical filtration process of converting Cr VI to Cr III which is comparatively less harmful than Cr VI. The execution of such mechanical processing is not practically feasible so industries have begun to drift towards bio treatment. In general, the literature of earlier works sketch out many merits of switching from mechanical to bio processing, but the most influencing merit has not yet clearly stated. Therefore this research work is an effort of determining it so as to stimulate it for mitigating the toxicity in a most comprehensive manner. In order to accomplish this task systematically, the mathematical tool, Fuzzy Cognitive Map is used in this paper.
This paper reflects on how some Artificial Intelligence Techniques
may positively affect the operation of a distance education platform.
It addresses to a particular distance education platform at which
specific characteristics are incorporated, such as the adaptation to different
users profiles as much to diagnose as to determine a plan for the most
adequate teaching strategies. The use of Bayes nets and neural networks
are mentioned in the evaluation process and a summarized example is
included in the use of the platform.
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.
Frontiers of ICT in Healthcare
Cities are increasingly looking to become smarter and more resilient. Also, the use of computer vision takes a considerable place in the panoply of techniques and algorithms necessary for the 3D reconstruction of urban built environments. The models thus obtained make it possible to feed the logic of decision support and urban services thanks to the integration of augmented reality. This chapter describes and uses Fuzzy Cognitive Maps (FCM) as computing framework of visual features matching in augmented urban built environment modeling process. It is a combination of the achievements of the theory of fuzzy subsets and photogrammetry according to an algorithmic approach associated with the ARKit renderer. In this experimental research work, part of which is published in this chapter, the study area was confined to a portion of a housing estate and the data acquisition tools are in the domain of the public. The aim is the deployment of the algorithmic process to capture urban environments built in an augmented reality model and compute visual feature in stereovision within FCM framework. The comparison of the results obtained with our approach to two other well-known ones in the field, denotes the increased precision gain with a scalability factor.
ResearchGate has not been able to resolve any references for this publication.