Fuzzy-based Model Research Articles

Implementation of Fuzzy-based Model for Prediction of Prostate Cancer

Cancer is one of the leading causes of death worldwide. One type of cancer that causes death in the male population is prostate cancer. This disease occurs only in men because in women they do not have a prostate appearance. The aim of this study was to compare the accuracy of the model with the predictions of prostate cancer specialists. Prediction is made based on prostate specific antigen data, age, and patient prostate volume. The independent variables in this study were prostate specific antigen, age, and prostate volume. The dependent variable is the risk of prostate cancer using a fuzzy model. The novelty of this study is that the model has a low, moderate, high, and very high prostate cancer risk level output. In the previous article only PCR values were produced. The results show that the proposed fuzzy model provides a PCR value that is within the PCR interval predicted by a specialist doctor can be used properly to help diagnose and analyze the possibility of prostate cancer and is one of the considerations for doctors to decide whether or not a biopsy is needed for these patients.

Implementation of Fuzzy-based Model for Prediction of Thalassemia Diseases

Thalassemia is known as one of the blood disorder diseases that is inherited by parents. There are several types of Thalassemia, namely as Thalassemia major, minor, and intermedia. Among them, Thalassemia major is the most dangerous and needs more attention. Generally, it can be detected since the child is one year old. Late detection of this disease can have adverse consequences and various complications. This study aims to develop a new model for the prediction of thalassemia for children. The model adopts a fuzzy-based rule. The novelty in this article is that our model has 4 outputs, namely thalassemia major, intermedia, minor and not thalassemia. In the previous article it only had 3 outputs. In this study, we intend to implement a model that we developed using a fuzzy-based approach to classify thalassemia diseases based on CBC data. This article describes how to build a model and implement it in software. We compare the test results with the opinion of pediatricians regarding thalassemia. The final results of testing 4 CBC data show that our proposed model has successfully identified the type of thalassemia.

Embedded fuzzy-based models in hydraulic jump prediction

Abstract This study aims to evaluate the learning ability and performance of five meta-heuristic optimization algorithms in training forward and recurrent fuzzy-based machine learning models, such as adaptive neuro-fuzzy inference system (ANFIS) and RANFIS (recurrent ANFIS), to predict hydraulic jump characteristics, i.e., downstream flow depth (h2) and jump length (Lj). To meet this end, the firefly algorithm (FA), particle swarm algorithm (PSO), whale optimization algorithm (WOA), genetic algorithm (GA), and moth-flame optimization algorithm (MFO) are embedded with the fuzzy-based models, which represent the main contribution of this study. The analysis of the results of predicting hydraulic jump characteristics shows that the embedded ANFIS and RANFIS models are more accurate than the empirical relations proposed by the previous researchers. Comparing the performance of the embedded RANFISs and ANFISs methods in predicting Lj represents the superiority of the RANFIS models to the ANFISs. The results of the sensitivity analysis show that among the input independent parameters, flow discharge (Q) is the most important factor in predicting downstream flow depth in weak, oscillating, and steady hydraulic jumps (1.7 < Froude number < 9), while the upstream flow depth (h1) is more important than the other input parameters in strong hydraulic jumps (Froude number > 9).

Reimaging stakeholder analysis in project management: network theory and fuzzy logic applications

PurposeThe methods presently used for project stakeholder analysis have typically followed two distinct patterns: (1) a project-centric approach that places a project at the center, and subsequently, concentrates on dyadic relationships between the project and its stakeholders; (2) a network theory-based approach that emphasizes on the interconnections within the network of project stakeholders. The main contention of this study is built upon the premise that neither the sole analysis of dyadic relationships between a project and its stakeholders nor the stand-alone use of the network theory methods is adequate for reliable analysis of stakeholders.Design/methodology/approachThis article proposes a model that bases the salience of stakeholders on their relationships with the project as well as on their interdependencies in the project. In doing so, this work explores the potential of a Fuzzy Inference System (FIS) to provide a comprehensive picture of stakeholder analysis. Using a real-world biodiversity project, this paper analyses the project stakeholders based on their possession of various attributes as well as the extent to which each individual stakeholder influences the entire connected network of all stakeholders.FindingsA salient feature of the proposed FIS model is its ability to provide a high capacity for analyzing the results. The model is able to generate the input–output relationship surface view for stakeholder analysis. Further, unlike the traditional project stakeholder analysis methods that are linear, the proposed model is strongly nonlinear. This implies that change in the input variables of the fuzzy-based model is not expected to lead to a proportional change in the model output.Practical implicationsTwo practical implications can be drawn from the presented stakeholder analysis model. First, confronted with mounting pressure to understand the stakeholder environment and to effectively manage stakeholders, project managers need to establish a sound stakeholder management strategy. The stakeholder analysis model developed herein casts a wider net for the critical ranking of stakeholders in a project, thereby providing a more accurate prioritization of the stakeholders. Second, while stakeholders independently require managerial attention, understanding the effect of competing and cooperative stakeholder interactions are unarguably of great importance. The presented model prompts the project managers to recognize not only the influence of key stakeholders on the project but also the interactions of multiple stakeholders within the stakeholder network.Originality/valueThe proposed stakeholder analysis model possesses several desirable features. First, it is not constrained to capturing only stakeholder attributes discussed in the example project provided in this study. The model is flexible and adaptable to all business and management contexts. Second, the stakeholder mapping in the model is not a function of a sole attribute but rather a cumulative effect of multiple stakeholder attributes. In fact, the power of the suggested model lies in its ability to incorporate the three aspects of stakeholder theory into a single model. Third, the presented model builds a quantitative and qualitative picture of the stakeholder salience. The suggested FIS model is capable of processing both qualitative perception of stakeholder attributes and quantitative analysis of the network of stakeholder interactions. This allows for a more comprehensive and synergistic utilization of model inputs.

An Adaptive Fuzzy Modeling of Visual Attention in Real-world Interaction with Health Information System

Bottom-up and top-down processes are the two mechanisms of visual attention allocation, which allow people to efficiently spot task-relevant stimuli from cluttered and noisy environments, while staying alert to abnormalities within the visual field of view. This paper presents a preliminary study of the physicians’ real-life interaction with Information Communication Technology (ICT) in their own offices, along with extensively analyzing one case of an hour-long interaction of a physician, in which one performs a daily routine of reviewing patient electronic health records (EHRs) and writing diagnostic notes to the system interface. The physician interactions were captured in a time series data by recording display screen, keystrokes and mouse movements, also by simultaneously tracking eye movements. Then, a fuzzy-based model that can distinguish bottom-up and top-down processes were defined by using statistical random variables in terms of eye-movement patterns. The shift between those two attentional processes was detected by tracking the parametric changes of gaze behaviors as input: significant shift of fixation, sustained gazing, and fixation trajectory over time. Based on those gaze metrics, a random variable was assigned to the discrete probability of low (0), medium (0.5), or high (1.0), for a quantified fuzzy output, which was further machine-learned into an Adaptive Neuro-Fuzzy Inference System (ANFIS) model in order to judge how a physician is likely to be dominated by a bottom-up or top-down processes in performing a task at that instance in time. On training the ANFIS model with three different types of fuzzy membership functions (Gaussian, triangular and trapezoidal), the model performed best with the Gaussian function (after 100 iterations, the predicted root mean-square error (RMSE) converged at 0.07%, yielding a smooth linear curve). For a proof-of concept, the model was implemented by using one physician’s gaze behaviors, of which the average, machine-learned fuzzy output probability indicated that the physician was veering toward bottom-up visual attention. This individualized, task-specific pattern of visual attention has implications for the designs of intelligent interface in ICT. Our ANFIS model can scale up to different physicians and tasks to predict the likelihood of bottom-up or top-down information processing based on real-world gaze behaviors.

An Adaptive General Type-2 Fuzzy Logic Approach for Psychophysiological State Modeling in Real-Time Human–Machine Interfaces

In this article, a new type-2 fuzzy-based modeling approach is proposed to assess human operators’ psychophysiological states for both safety and reliability of human–machine interface systems. Such a new modeling technique combines type-2 fuzzy sets with state tracking to update the rule base through a Bayesian process. These new configurations successfully lead to an adaptive, robust, and transparent computational framework that can be utilized to identify dynamic (i.e., real time) features without prior training. The proposed framework is validated on mental arithmetic cognitive real-time experiments with ten participants. It is found that the proposed framework outperforms other paradigms (i.e., an adaptive neuro-fuzzy inference system and an adaptive general type-2 fuzzy c-means modeling approach) in terms of disturbance rejection and learning capabilities. The proposed framework achieved the best performance compared to other models that have been presented in the related literature. Therefore, the new framework can be a promising development in human–machine interface systems. It can be further utilized to develop advanced control mechanisms, investigate the origins of human compromised task performance, and identify and remedy psychophysiological breakdown in the early stages.

A Fuzzy-Based Multi-Modal Architectural Model for Electioneering in Nigeria

The 2015 election has been adjured to be the best in the history of elections in Nigeria, thanks to the deployment of information technology by the Independent National Electoral Commission (INEC). In reality, the election was not as flawless as many people believe. There were lots of problems associated with it, particularly in the areas of verification and authentication of eligible voters. This work examines these problems and proposed a fuzzy-based multi-modal architectural model for future elections in contrast to the unimodal model currently in use. The architecture is based on the extraction of the features of fingerprint and iris of the prospective voters as opposed to only fingerprint currently in use. Drawing from the strength of fingerprint and Iris features discussed in the work, a robust architecture supported by the fuzzy-based mathematical model was developed for future elections. Further discussed were the advantages of the proposed architecture over the current INEC method of voter verification and authentication.

Fuzzy-based Description of Computational Complexity of Central Nervous Systems

Computational intelligence algorithms are currently capable of dealing with simple cognitive processes, but still remain inefficient compared with the human brain’s ability to learn from few exemplars or to analyze problems that have not been defined in an explicit manner. Generalization and decision-making processes typically require an uncertainty model that is applied to the decision options while relying on the probability approach. Thus, models of such cognitive functions usually interact with reinforcement-based learning to simplify complex problems. Decision-makers are needed to choose from the decision options that are available, in order to ensure that the decision-makers’ choices are rational. They maximize the subjective overall utility expected, given by the outcomes in different states and weighted with subjective beliefs about the occurrence of those states. Beliefs are captured by probabilities and new information is incorporated using the Bayes’ law. Fuzzy-based models described in this paper propose a different – they may serve as a point of departure for a family of novel methods enabling more effective and neurobiologically reliable brain simulation that is based on fuzzy logic techniques and that turns out to be useful in both basic and applied sciences. The approach presented provides a valuable insight into understanding the aforementioned processes, doing that in a descriptive, fuzzy-based manner, without presenting a complex analysis

A fuzzy inference system (FIS) to evaluate the security readiness of cloud service providers

Cloud computing is a model for on-demand delivery of IT resources (e.g., servers, storage, databases, etc.) over the Internet with pay-as-you-go pricing. Although it provides numerous benefits to cloud service users (CSUs) such as flexibility, elasticity, scalability, and economies of scale, there is a large trust deficit between CSUs and cloud service providers (CSPs) that prevents the widespread adoption of this computing paradigm. While some businesses have slowly started adopting cloud computing with careful considerations, others are still reluctant to migrate toward it due to several data security and privacy issues. Therefore, the creation of a trust model that can evolve to reflect the true assessment of CSPs in terms of either a positive or a negative reputation as well as quantify trust level is of utmost importance to establish trust between CSUs and CSPs. In this paper, we propose a fuzzy-logic based approach that allows the CSUs to determine the most trustworthy CSPs. Specifically, we develop inference rules that will be applied in the fuzzy inference system (FIS) to provide a quantitative security index to the CSUs. One of the main advantages of the FIS is that it considers the uncertainties and ambiguities associated with measuring trust. Moreover, our proposed fuzzy-logic based trust model is not limited to the CSUs as it can be used by the CSPs to promote their services through self-evaluation. To demonstrate the effectiveness of our proposed fuzzy-based trust model, we present case studies where several CSPs are evaluated and ranked based on the security index.

FBPCQS-Fuzzy-Based Peer Coordination Quality Systems for P2P Networks

This work presents a distributed event-based awareness approach for P2P groupware systems. The authors present two fuzzy-based systems for improving peer awareness and group synchronization according to four parameters: activity awareness (AA), sustained communication time (SCT), group synchronization (GS), and peer communication cost (PCC). Then, this research uses fuzzy-based model to decide peer coordination quality (PCQ). The authors call the proposed systems: fuzzy-based peer coordination quality (FBPCQ) systems (FBPCQS1 and FBPCQS2). The authors make a comparison study between FBPCQS1 and FBPCQS2. The simulations results conclude that when AA, GS, and SCT are high, the PCQ is high, but with increasing of the PCC, the PCQ is decreased. The proposed systems can choose reliable peers with good peer coordination quality in mobilePeerDroid mobile system. Comparing the complexity, the FBPCQ2 is more complex than FBPCQS1. However, FBPCQS2 considers also the PCC, which makes the system more reliable.

Measuring the smartness of a library

Traditional libraries around the world are integrating cutting-edge technologies, such as data mining, artificial intelligence, Internet of Things, and voice-based search, to transform themselves into smart libraries. However, what elements make a library smart? How does one estimate the smartness of a library? To address these fundamental questions five elements and fifteen subelements that make a library smart were identified from a comprehensive review of the literature. A fuzzy-based model for use computing a library's smartness index was developed around these elements/subelements. Ease of use of this model was demonstrated by applying it to measure the smartness of a large academic library in South Asia.

A fuzzy inference system for predicting pavement surface damage due to combined action of traffic loading and water

ABSTRACT This paper presents a fuzzy logic-based deterioration prediction models for gap and open-graded asphalt surfaces when both dynamic loading and shallow flooding coincide. The impact of aggregate size, load frequency, compaction levels, and environmental conditions was evaluated in a controlled laboratory testing to measure cracking and rutting performance of each mixture. A set of fuzzy logic was developed using the experimental data and then tested against randomly selected samples. The predicted cracking and rutting showed excellent agreements (95% correlation) with the experimentally measured values. The validation and sensitivity analysis showed that irrespective of aggregate gradation, mixture parameters (aggregate size, void contents), traffic parameters (loading frequency) and environmental factors (wet and dry condition) have a significant impact on model performance. Overall, the Fuzzy-based prediction model showed the potential to differentiate the performance of different asphalt surfaces and can be further developed to use in practical applications.

Fuzzy-Based Model for Predicting Strength of Geogrid-Reinforced Subgrade Soil with Optimal Depth of Geogrid Reinforcement

A fuzzy logic (FL)–based modeling approach is employed for geogrid-reinforced subgrade soil of unpaved roads. A review of the literature reveals that fuzzy logic has not been used for predicting the behavior of geogrid-reinforced subgrade. This paper presents FL-based two models with fuzzy Triangular and Gaussian membership functions for input and output variables. It consists of eight input parameters/factors, namely, reinforced/unreinforced section, depth of reinforcement, liquid limit, plastic limit, plasticity index, optimum moisture content, maximum dry unit weight, and soaked/unsoaked condition, and California bearing ratio (CBR) as an output parameter. The fuzzy rules are deduced from the experimental data. The laboratory CBR tests were performed on the subgrade soil reinforced with geogrid. The precision of models was examined by comparing the predicted CBR values with the experimental CBR values for Triangular and Gaussian membership functions. The sensitivity analysis reflects a set of dominant parameters. The results indicated a significant improvement in the CBR value of geogrid-reinforced subgrade soil due to the inclusion of geogrid. The range for optimal depth of geogrid reinforcement is found to be 36 to 60% of the thickness of the soil layer. The potentialities of FL were found to be satisfactory.

Neural fuzzy approximation enhanced autonomous tracking control of the wheel-legged robot under uncertain physical interaction

The accuracy of trajectory tracking and stable operation with heavy load are the main challenges of parallel mechanism for wheel-legged robots, especially in complex road conditions. To guarantee the tracking performance in an uncertain environment, the disturbances, including the internal-robot friction and external-robot and environment interaction forces, should be considered in the robot’s dynamical system. In this article, a neural fuzzy-based model predictive tracking scheme (NFMPC) for reliable tracking control is proposed to the developed four wheel-legged robot, and the fuzzy neural network approximation is applied to estimate the unknown physical interaction and external dynamics of the robot system. Meanwhile, the advanced parallel mechanism of the four wheel-legged robot (BIT-NAZA) is introduced. Finally, co-simulation and experiment results using the BIT-NAZA robot derived from the proposed hybrid control strategy indicate that the methodology can achieve satisfactory tracking performance in terms of accuracy and stability. This research can provide theoretical and engineering guidance for lateral stability of intelligent robots under unknown disturbances and uncertain nonlinearities, and facilitate the control performance of the wheel-legged robot in a practical system.

Further Stability and Stabilization Condition for Sampled-Data Control Systems via Looped-Functional Method

This brief contributes the further results on stability and stabilization conditions for sampled-data-based control systems (SDCSs), which include linear SDCSs and nonlinear SDCSs via looped-Lyapunov functional approach. The improved Lyapunov functional involves the states information such as $x(t_{k})$ and $x(t_{k+1})$ with few slack variables and a tuning parameter. The sufficient conditions are derived for both linear SDCSs and nonlinear SDCSs, whereas Takagi-Sugeno (T-S) approach is employed to express the nonlinear SDCS into T-S fuzzy-based model through fuzzy IF-THEN membership rules. With the derived conditions, the stability region of the proposed SDCSs can be enhanced and their asymptotic stability will be ensured. Finally, the numerical analysis is performed with the existing models and their corresponding performances are provided to validate the less conservatism and superiority of the derived results over the existing ones.

An automated model to score the privacy of unstructured information—Social media case

One of the common forms of data which is shared by online social media users is free-text formats including comments, posts, blogs and tweets. While users mostly share this unstructured data with their preferred social groups, this textual data may contain sensitive information such as their political or religious views, job details, their opinions and emotions and so on. Hence, sharing this unstructured data can escalate privacy risks and concerns for social media users. Analyses the privacy of unstructured data occurred from textual information comes with difficulties as understanding the calculation metrics are challenging. Although there are various studies on privacy evaluation from the extracted structured information from unstructured data, there are limited privacy scoring methods concentrating on the views of the individuals and cannot satisfy the privacy scoring of shared unstructured data in social networks appropriately. Here, in this paper, we propose an automated fuzzy-based model that can extract the privacy-related features as well as the related shared structured data and measure and warn users regarding the textual data privacy risks they have shared in online social platforms. The proposed model can facilitate mitigation actions for users’ free-format texts shared in various social networks. The evaluation of the study indicates that the proposed model can measure the users’ privacy risk in a more accurate manner compared with previously proposed methods and available commercialised software in the domain.

Sustainability Ranking of Desalination Plants Using Mamdani Fuzzy Logic Inference Systems

As water desalination continues to expand globally, desalination plants are continually under pressure to meet the requirements of sustainable development. However, the majority of desalination sustainability research has focused on new desalination projects, with limited research on sustainability performance of existing desalination plants. This is particularly important while considering countries with limited resources for freshwater such as the United Arab Emirates (UAE) as it is heavily reliant on existing desalination infrastructure. In this regard, the current research deals with the sustainability analysis of desalination processes using a generic sustainability ranking framework based on Mamdani Fuzzy Logic Inference Systems. The fuzzy-based models were validated using data from two typical desalination plants in the UAE. The promising results obtained from the fuzzy ranking framework suggest this more in-depth sustainability analysis should be beneficial due to its flexibility and adaptability in meeting the requirements of desalination sustainability.

A fuzzy-based roadmapping model for enhancing high-tech small firms’ technological entrepreneurship capabilities: cases of Iran

ABSTRACTTechnology-based firms need to survive via technological changes. Technological entrepreneurship is concentrated on identifying and exploiting the tech-opportunities for creating product innovation. This paper introduces a fuzzy-based tool to promote innovation throughout firms in order to enhance technological entrepreneurship capabilities (TEC). The effort involves identifying components of TEC to develop the inference system, specifying the fuzzy relationship among these components, assessing the TEC in firms, and designing a TEC roadmap after a fuzzy-based gap analysis. Designed roadmaps introduce technological change priorities as a growth path to firms to move up along the ladder of competitiveness. Based on the results, a method for categorizing firms into four distinct levels that involve passive, reactive, proactive and innovative is introduced. Hence, firms have an action plan to enhance TEC from passive to innovative level in a time-based transition pathway.

Prediction of greenhouse gas emissions from Ontario's solid waste landfills using fuzzy logic based model

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

Modelling and optimization of dye removal by Fe/Cu bimetallic nanoparticles coated with different Cu ratios

As the pollution from textile wastewater amount increases each year, discharge threshold values are reduced by regulations in order to limit receptor mass loading. This situation reveals the necessity of introducing innovative solutions instead of traditional systems in the treatment of textile wastewater. In the present study, we implemented dye removal by synthesized Fe/Cu bimetallic nanoparticles. Then, a multiple fuzzy-based model was applied in order to estimate colour removal. Initial colour concentration, pH, reaction time, Cu ratio on Fe/Cu nanoparticle, and Fe/Cu nanoparticle concentrations were selected as independent variables and fuzzified in an artificial intelligence-based approach. A mamdani-type fuzzy interface system was used. Input and output variables were designed with Gaussian membership functions. The predicted results gathered from fuzzy-logic system and the experimental results were compared with multiple regression approach. The regression coefficient was obtained as 0.992. According to multiple regression results, the most effective input variable was determined as the Cu ratio on Fe/Cu nanoparticle. The optimum conditions were also concluded via MathCad program. The highest removal efficiency was attained with 5% Cu ratio on Fe/Cu nanoparticle at 200 mg L−1 concentration. Furthermore, the prepared fuzzy-logic modelling demonstrated that the removal of dye by Fe/Cu nanoparticles is suitable for modelling.