Fuzzy Pattern Research Articles

Analysis of fluid property variations across the Barnett and Eagle Ford Shale using fuzzy logic

The objective for this study is to perform an investigation of the areal and vertical geospatial fluid property variations across the Barnett and Eagle Ford based on publicly-available PVT data (97 Barnett wells and 153 Eagle Ford wells). A modified multi-contact recombination procedure has been implemented to the PVT data of the reported well stream compositions for Barnett to improve estimates of in-situ reservoir composition. The Eagle Ford data were utilised without modifications as this shale play is known to be highly under-saturated. The results of modified multi-contact recombination procedure for Barnett are plotted on a ternary diagram and show that the majority of the wells were dry gas to retrograde gas. For Eagle Ford, ternary diagrams indicated the fluid type, vertical variations of OGR, C7+ and API gravity. Maps were created to review areal variations of these properties (API gravity, C7+, and initial OGR). The study was further speculated by applying fuzzy pattern recognition algorithms. The application of fuzzy logic provided additional insight to the reservoir fluid's PVT behaviour in understudy shale formations. [Received: August 23, 2018; Accepted: May 6, 2019]

Analysis of fluid property variations across the Barnett and Eagle Ford Shale using fuzzy logic

The objective for this study is to perform an investigation of the areal and vertical geospatial fluid property variations across the Barnett and Eagle Ford based on publicly-available PVT data (97 Barnett wells and 153 Eagle Ford wells). A modified multi-contact recombination procedure has been implemented to the PVT data of the reported well stream compositions for Barnett to improve estimates of in-situ reservoir composition. The Eagle Ford data were utilised without modifications as this shale play is known to be highly under-saturated. The results of modified multi-contact recombination procedure for Barnett are plotted on a ternary diagram and show that the majority of the wells were dry gas to retrograde gas. For Eagle Ford, ternary diagrams indicated the fluid type, vertical variations of OGR, C7+ and API gravity. Maps were created to review areal variations of these properties (API gravity, C7+, and initial OGR). The study was further speculated by applying fuzzy pattern recognition algorithms. The application of fuzzy logic provided additional insight to the reservoir fluid's PVT behaviour in understudy shale formations. [Received: August 23, 2018; Accepted: May 6, 2019]

Smart Helmet: Thresh-Learner–Online Machine Learning on Data Streams

Today, with an enormous generation and availability of time series data and streaming data, there is an increasing need for an automatic analyzing architecture to get fast interpretations and results. One of the significant potentiality of streaming analytics is to train and model each stream with unsupervised Machine Learning (ML) algorithms to detect anomalous behaviors, fuzzy patterns, and accidents in real-time. If executed reliably, each anomaly detection can be highly valuable for the application. In this paper, we propose a dynamic threshold setting system denoted as Thresh-Learner, mainly for the Internet of Things (IoT) applications that require anomaly detection. The proposed model enables a wide range of real-life applications where there is a necessity to set up a dynamic threshold over the streaming data to avoid anomalies, accidents or sending alerts to distant monitoring stations.We took the major problem of anomalies and accidents in coal mines due to coal fires and explosions. This results in loss of life due to the lack of automated alarming systems. We propose Thresh-Learner, a general purpose implementation for setting dynamic thresholds. We illustrate it through the Smart Helmet for coal mine workers which seamlessly integrates monitoring, analyzing and dynamic thresholds using IoT and analysis on the cloud.

Artificial Bee Colony Algorithm for Solving Fuzzy Multi-Objective Bed Allocation Model

With the improvement of the medical services frameworks rivalry, hospitals face more and more challenges. In the interim, allotment of resource has a crucial influence on performing competitive benefits in a hospitals. To choose the suitable beds number is one of the most essential tasks in hospital administration. Anyway, in true condition, bed allotment choice is a multiple-side problem with weakness and haphazardness of the information available. It is so sophisticated. Therefore, the research about bed allotment difficulty is comparatively rare under considering multiple departments, nursing hours, and stochastic information about arrival and service of patients. In this paper, we improve a fuzzy multi-objective bed allotment pattern for defeating doubtfulness and various sections. Fuzzy objectives, and weights are at the same time used to assist the administrators to choose the appropriate beds about various departments. The suggested pattern uses Artificial Bee Colony (ABC), which is so efficient algorithm. The research portrays a use of the pattern in a public hospital in Iraq. The outcome has shown presented an appropriate system for bed allotment and ideal usage.

Electroencephalogram Based Reaction Time Prediction With Differential Phase Synchrony Representations Using Co-Operative Multi-Task Deep Neural Networks

Driver drowsiness is receiving a lot of deliberation as it is a major cause of traffic accidents. This paper proposes a method which utilizes the fuzzy common spatial pattern optimized differential phase synchrony representations to inspect electroencephalogram (EEG) synchronization changes from the alert state to the drowsy state. EEG-based reaction time prediction and drowsiness detection are formulated as primary and ancillary problems in the context of multi-task learning. Statistical analysis results suggest that our method can be used to distinguish between alert and drowsy state of mind. The proposed Multi-Task DeepNet (MTDNN) performs superior to the baseline regression schemes, like support vector regression (SVR), least absolute shrinkage and selection operator, ridge regression, K-nearest neighbors, and adaptive neuro fuzzy inference scheme (ANFIS), in terms of root mean squared error (RMSE), mean absolute percentage error (MAPE), and correlation coefficient (CC) metrics. In particular, the best performing multi-task network MTDNN5 recorded a 15.49% smaller RMSE, a 27.15% smaller MAPE, and a 10.13% larger CC value than SVR.

Logical analysis of multiclass data with relaxed patterns

An efficient and robust algorithm based on mixed integer linear programming is proposed to extend the Logical Analysis of Data (LAD) methodology to solve multiclass classification problems, where One-vs-Rest learning models are constructed to classify observations in predefined classes. The proposed algorithm uses two control parameters, homogeneity and prevalence, for identifying relaxed (fuzzy) patterns in multiclass datasets. The utility of the proposed method is demonstrated through experiments on multiclass benchmark datasets. Numerical experiments show that the efficiency and performance of the proposed multiclass LAD method with relaxed patterns is comparable to, if not better than, those of the previously developed LAD based multiclass classification as well as other well-known supervised learning methods.

Formula omitted]: Language pattern learning for word sense induction and disambiguation

Identifying the correct meaning of words in context or discovering new word senses is particularly useful for several tasks such as question answering, information extraction, information retrieval, and text summarization. However, specially in the context of user-generated contents and on-line communication (e.g. Twitter), new meanings are continuously crafted by speakers as the result of existing words being used in novel contexts. Consequently, lexical semantics inventories and systems have difficulties to cope with semantic drifting problems. In this work, we propose an approach to induce and disambiguate word senses of some target words in collections of short texts, such as tweets, through the use of fuzzy lexico-semantic patterns that we define as sequences of Morpho-semantic Components (MSC). We learn these patterns, that we call MSC+ patterns, from text data automatically. Experimental results show that instances of some MSC+ patterns arise in a number of tweets, but sometimes using different words to convey the sense of the respective MSC in some tweets where pattern instances appear. The exploitation of MSC+ patterns when they induce semantics on target words enable effective word sense disambiguation mechanisms leading to improvements in the state of the art.

Probabilistic Forecasting With Fuzzy Time Series

In recent years, the demand for developing low computational cost methods to deal with uncertainties in forecasting has been increased. Probabilistic forecasting is a class of forecasting in which the method provides intervals or probability distributions as outcomes of its forecasting. The aim of this paper is, therefore, proposing a new forecasting approach based on fuzzy time series (FTS) that takes advantage of fuzzy and stochastic patterns on data and is capable to deal with point, interval, and distribution forecasts. The method proposed was empirically tested with typical financial time series, and the results were compared with other standard FTS and statistical methods. The results show that the proposed method obtained accurate results and outperformed standard FTS methods. The proposed method also combines versatility, scalability, and low computational cost, making it useful on a wide range of application scenarios.

A fuzzy decision system for money investment in stock markets based on fuzzy candlesticks pattern recognition

This article proposes a novel fuzzy recommendation system for stock market investors. This intelligent decision tool uses fuzzy Japanese candlesticks and includes the effect of currency devaluation on the forecasting. To do so, first the next market session is obtained by a new designed fuzzy forecasting trading system. Then, it is compared to the one obtained by a non-parametric system based on the k-nearest neighbor technique. Finally, an amount of money to be invested is considered using a new capital management fuzzy strategy. The results have been compared to an analogous fuzzy trading system that has the same all-or-nothing investment strategy with risk control, but where this capitalization is not included. Both intelligent decision systems have been applied to two very different stock markets, the American Nasdaq100 and the Spanish Ibex35 markets, using the Buy and Hold investment strategy as benchmark. Results prove that the proposed fuzzy system with capitalization is profitable and presents high stability, and could be a good support system for investors.

Fuzzy flow pattern identification in horizontal air-water two-phase flow based on wire-mesh sensor data

Online monitoring of two-phase flow patterns is an essential need in various chemical engineering applications, since the reliability of prediction methods is limited. Therefore, the present study aims at developing a practically applicable algorithm for identifying flow patterns in horizontal gas-liquid flows on the basis of wire-mesh sensor data. Experiments were conducted in a 50 mm i. d. pipe over a wide range of superficial velocities of an air-water mixture. Characteristic features involving the influence of gravity and the spatio-temporal behavior of the flows were derived from tomographic phase fraction data and used as input for fuzzy clustering. Three differently determined sets of cluster centers are compared against a reference classification by human specialist through reclassifying the measurements with the aid of defuzzyfication and, alternatively, by means of a novel visualization technique, that retains the fuzziness of the results. With respect to the latter one, best agreement is reached with cluster centers from fuzzy c-means clustering using all recorded measurements. As a special emphasis is put to the identification of transitional flow patterns, the performance of the algorithm at pseudo-dynamic operation is demonstrated, finally.

IRIS RECOGNITION USING WAVELET TRANSFORM AND SVM BASEDAPPROACH

Inthis paper we proposed an improved novel approachto identify the person using iris recognition technique. Thisapproach is based on fuzzy and support vector machine (SVM) asan iris pattern classifier. Prior to classifier, region of interest i.e.iris region is segmented using Canny edge detector and Houghtransform. Provided that the effect of eyelid and eyelashes getreduced. Daugman’s rubber sheet model used to get normalized iristo improve computational efficiency and proper dimensionality.Further, discriminating feature sequence is obtained by featureextraction from segmented iris image using 1D Log Gaborwavelet.Encoding is done using phase quantization to get featurevectors. These binary sequence feature vectors are used to trainSVM and fuzzy system as iris pattern classifier. The experimentaltests are performed over standard CASIAIrisV4 database.

Fuzzy pattern tree for edge malware detection and categorization in IoT

The surging pace of Internet of Things (IoT) development and its applications has resulted in significantly large amounts of data (commonly known as big data) being communicated and processed across IoT networks. While cloud computing has led to several possibilities in regard to this computational challenge, there are several security risks and concerns associated with it. Edge computing is a state-of-the-art subject in IoT that attempts to decentralize, distribute and transfer computation to IoT nodes. Furthermore, IoT nodes that perform applications are the primary target vectors which allow cybercriminals to threaten an IoT network. Hence, providing applied and robust methods to detect malicious activities by nodes is a big step to protect all of the network. In this study, we transmute the programs’ OpCodes into a vector space and employ fuzzy and fast fuzzy pattern tree methods for malware detection and categorization. We obtained a high degree of accuracy during reasonable run-times especially for the fast fuzzy pattern tree. Both utilized feature extraction and fuzzy classification, which were robust, led to more powerful edge computing malware detection and categorization method.

Option pricing and the Greeks under Gaussian fuzzy environments

This work considers pricing European call options and the study of Greek letters of options under a fuzzy environment. In the past work, stock prices are usually represented by symmetric triangular fuzzy numbers for the computational convenience while pricing options with uncertainty. It might not be enough to explain the stochastic nature of the underlining price in the option pricing formula. This work considers developing the fuzzy pattern of European call option under the assumption of the stock return being a Gaussian fuzzy number. The study of Greeks for the sensitivity analysis of the fuzzy call option price with respect to the change in the pricing variables is included. The empirical analysis and comparison on the fuzzy European option pricing based on the real market data of SPX options at CBOE are provided. Our results show that the fuzzy options are more close to the theoretical options derived from the Black–Scholes formula while employing Gaussian fuzzy stock returns for pricing European call options.

Methods Managing for Matching of Supply and Demand on the IT Specialists

The problem of the management of the IT specialists labor market is identified as ill-structured problem and reduced to the problem of decision-making based on selecting the policy for the matching of supply and demand. It also proposes the models for supply and demand in the IT Specialists labor market on the based fuzzy situation analysis, possible scenarios for the relationship between supply and demand are outlined. By taking into account the varying nature of the matching between supply and demand, fuzzy pattern recognition based decision-making methods have been developed for the IT Specialists staff recruitment.

Extreme Fuzziness: Direct Interactions between Two IDPs.

Protein interactions involving intrinsically disordered proteins (IDPs) greatly extend the range of binding mechanisms available to proteins. In interactions employing coupled folding and binding, IDPs undergo disorder-to-order transitions to form a complex with a well-defined structure. In many other cases, IDPs retain structural plasticity in the final complexes, which have been defined as the fuzzy complexes. While a large number of fuzzy complexes have been characterized with variety of fuzzy patterns, many of the interactions are between an IDP and a structured protein. Thus, whether two IDPs can interact directly to form a fuzzy complex without disorder-to-order transition remains an open question. Recently, two studies of interactions between IDPs (4.1G-CTD/NuMA and H1/ProTα) have found a definite answer to this question. Detailed characterizations combined with nuclear magnetic resonance (NMR), single-molecule Förster resonance energy transfer (smFRET) and molecular dynamics (MD) simulation demonstrate that direct interactions between these two pairs of IDPs do form fuzzy complexes while retaining the conformational dynamics of the isolated proteins, which we name as the extremely fuzzy complexes. Extreme fuzziness completes the full spectrum of protein-protein interaction modes, suggesting that a more generalized model beyond existing binding mechanisms is required. Previous models of protein interaction could be applicable to some aspects of the extremely fuzzy interactions, but in more general sense, the distinction between native and nonnative contacts, which was used to understand protein folding and binding, becomes obscure. Exploring the phenomenon of extreme fuzziness may shed new light on molecular recognition and drug design.

Novel Parameterized Utility Function on Dual Hesitant Fuzzy Rough Sets and Its Application in Pattern Recognition

Based on comparative studies on correlation coefficient theory and utility theory, a series of rules that utility functions on dual hesitant fuzzy rough sets (DHFRSs) should satisfy, and a kind of novel utility function on DHFRSs are proposed. The characteristic of the introduced utility function is a parameter, which is determined by decision-makers according to their experiences. By using the proposed utility function on DHFRSs, a novel dual hesitant fuzzy rough pattern recognition method is also proposed. Furthermore, this study also points out that the classical dual tool is suitable to cope with dynamic data in exploratory data analysis situations, while the newly proposed one is suitable to cope with static data in confirmatory data analysis situations. Finally, a medical diagnosis and a traffic engineering example are introduced to reveal the effectiveness of the newly proposed utility functions on DHFRSs.

New Fuzzy-Based Fault Tolerance Evaluation Framework for Cloud Computing

Fault tolerance is one of the principal challenges in cloud computing. This capability has a trade off with other system features. Providing a fuzzy inference system to evaluate fault tolerance architectural capabilities in cloud computing systems is among the goals of this research. The proposed system is called CFTFIS. It evaluates the fault tolerance architecture and determines the level of fault tolerance based on fuzzy patterns. Three parameters of each architecture, i.e., policies, fault detection and fault recovery techniques, have been considered. Fault tolerance of the presented architecture and the increased percentage of the intended capability are obtained at five different fuzzy levels. If the vulnerability of a cloud computing system is identified, it is possible to make a correct and proper choice of the architecture that should be implemented in the system. Additionally, if the damage to a cloud computing system is defined based on the amount and type of the faults, it is possible to choose an architecture and implement it in the system based on the fault tolerance that each architecture provides.

A similarity-based neuro-fuzzy modeling for driving behavior recognition applying fusion of smartphone sensors

Drivers’ behavior evaluation is one of the most important problems in intelligent transportation systems and driver assistant systems. It has a great influence on driving safety and fuel consumption. One of the challenges in this regard is the modeling perspective to treat with uncertainty in judgments about driving behaviors. Really, assessing a single maneuver with a rigid threshold leads to a weak judgment for driving evaluation. To fill this gap, a novel neuro-fuzzy system is proposed to classify the driving behaviors based on their similarities to fuzzy patterns when all of the various maneuvers are stated with some fuzzy numbers. These patterns are also fuzzy numbers and they are extracted from statistical analysis on the smartphone sensors data. Our driving evaluation system consists of three processes. Firstly, it detects the type of all of the maneuvers through the driving period, by using a multi-layer perceptron neural network. Secondly, it extracts a new feature based on the acceleration and assigns three fuzzy numbers to driver’s lane change, turn and U-turn maneuvers. Thirdly, it determines the similarity between these three fuzzy numbers and the fuzzy patterns to evaluate the safe and the aggressive driving scores. To validate this model, Driver’s Angry Score (DAS) questionnaires are used. Results show that the fusion of Inertial Measurement Unit (IMU) sensors of smartphones is enough for the proposed driving evaluation system. Accuracy of this system is 87% without using GPS and GIS data and this system is independent of smartphones and vehicles types.

A novel fuzzy convolutional neural network for recognition of handwritten Marathi numerals

Pattern classification is the approach of designing a method to map the inputs to the matching output classes. A novel fuzzy convolutional neural network (FCNN) is proposed in this paper for recognition of handwritten Marathi numerals. FCNN uses fuzzy set hypersphere as a pattern classifier to map inputs to classes represented by the combination of the fuzzy set hypersphere. Given labelled classes, the model designed proved efficient with 100% accuracy on the training set. The two major factors which improve the learning algorithm of FCNN are: 1) extract the dominant features from numeral image patterns using customised convolutional neural network (CCNN); 2) supervised clustering is used to create a new fuzzy hypersphere based on its distance measurement learning rules of fuzzy hypersphere neural network (FHSNN) and pattern classification done by the fuzzy membership function. Performance evaluation of model is done on Marathi numerals large datasets and its performance is found to be superior to traditional convolutional neural network (CNN) model. The obtained results demonstrate the fact that FCNN learning rules can be used as a useful representation for different classification pattern problems.

A novel fuzzy convolutional neural network for recognition of handwritten Marathi numerals

Pattern classification is the approach of designing a method to map the inputs to the matching output classes. A novel fuzzy convolutional neural network (FCNN) is proposed in this paper for recognition of handwritten Marathi numerals. FCNN uses fuzzy set hypersphere as a pattern classifier to map inputs to classes represented by the combination of the fuzzy set hypersphere. Given labelled classes, the model designed proved efficient with 100% accuracy on the training set. The two major factors which improve the learning algorithm of FCNN are: 1) extract the dominant features from numeral image patterns using customised convolutional neural network (CCNN); 2) supervised clustering is used to create a new fuzzy hypersphere based on its distance measurement learning rules of fuzzy hypersphere neural network (FHSNN) and pattern classification done by the fuzzy membership function. Performance evaluation of model is done on Marathi numerals large datasets and its performance is found to be superior to traditional convolutional neural network (CNN) model. The obtained results demonstrate the fact that FCNN learning rules can be used as a useful representation for different classification pattern problems.