Rule-based Fuzzy Inference System Research Articles

Fuzzy-based task offloading in Internet of Vehicles (IoV) edge computing for latency-sensitive applications

As vehicular applications continue to evolve, the computational capabilities of individual vehicles alone are no longer sufficient to meet the increasing demands. This has led to the integration of edge computing in the Internet of Vehicles (IoV) as an essential solution. Due to the limited resources within vehicles, there is often a need to offload tasks to edge nodes. However, task offloading in IoV environments presents several challenges, including high mobility, dynamic network topology, and varying node density. Traditional offloading methods fail to effectively address these challenges. Moreover, tasks differ in importance, necessitating a mechanism for edge nodes to prioritize tasks based on their urgency. To overcome these challenges, we propose a Vehicle-to-Vehicle (V2V) fuzzy-based task offloading scheme. In this scheme, fuzzy logic plays a critical role by enabling dynamic prioritization of tasks based on their urgency and the available computational resources at edge nodes, ensuring intelligent, context-aware decision-making. The user vehicle selects an appropriate edge node using an edge selection mechanism, which guarantees prolonged connection time and sufficient computational resources. Tasks at the edge are then organized based on their latency requirements and evaluated using a fuzzy rule-based inference system. Our simulation results demonstrate improved task execution rates, reduced overall system delay, and minimized queuing delays.

A dynamic fuzzy rule-based inference system using fuzzy inference with semantic reasoning

The challenge of making flexible, standard, and early medical diagnoses is significant. However, some limitations are not fully overcome. First, the diagnosis rules established by medical experts or learned from a trained dataset prove static and too general. It leads to decisions that lack adaptive flexibility when finding new circumstances. Secondly, medical terminological interoperability is highly critical. It increases realism and medical progress and avoids isolated systems and the difficulty of data exchange, analysis, and interpretation. Third, criteria for diagnosis are often heterogeneous and changeable. It includes symptoms, patient history, demographic, treatment, genetics, biochemistry, and imaging. Symptoms represent a high-impact indicator for early detection. It is important that we deal with these symptoms differently, which have a great relationship with semantics, vary widely, and have linguistic information. This negatively affects early diagnosis decision-making. Depending on the circumstances, the diagnosis is made solo on imaging and some medical tests. In this case, although the accuracy of the diagnosis is very high, can these decisions be considered an early diagnosis or prove the condition is deteriorating? Our contribution in this paper is to present a real medical diagnostic system based on semantics, fuzzy, and dynamic decision rules. We attempt to integrate ontology semantics reasoning and fuzzy inference. It promotes fuzzy reasoning and handles knowledge representation problems. In complications and symptoms, ontological semantic reasoning improves the process of evaluating rules in terms of interpretability, dynamism, and intelligence. A real-world case study, ADNI, is presented involving the field of Alzheimer’s disease (AD). The proposed system has indicated the possibility of the system to diagnose AD with an accuracy of 97.2%, 95.4%, 94.8%, 93.1%, and 96.3% for AD, LMCI, EMCI, SMC, and CN respectively.

Fuzzy inference system model for the spectrum characteristic periods of the Türkiye Building Earthquake Code (2007)

Seismic design codes define response spectra with crisp numerical classifications of seismic parameters, which mainly affect the spectrum's shape and determination of seismic design loads. The efficiency of structural safety and construction costs depends on the optimum design and accurately determined seismic forces. As presented in the seismic design codes, several parameters are utilized to calculate the seismic design forces with response spectra. This study proposes a rule-based fuzzy inference system (FIS) model with fuzzy set numbers to determine the relevant parameters. By defining the soil profile thickness and shear wave velocity as inputs, the model generates the spectrum characteristic periods specified in the Türkiye Building Earthquake Code (TBEC 2007). The response spectra of twenty different samples with the FIS and crisp models were generated and compared to assess the model's superiority. Unlike crisp seismic code classifications, the proposed FIS model accounts for imperfections in soil group selection and topmost soil layer thickness, offering a more realistic representation of uncertainties and proving to be an effective tool for addressing linguistic vagueness in seismic response spectra analysis. The comparison between fuzzy and crisp output seismic parameters revealed significant differences in response spectra shape and spectrum intensity values. The FIS model-generated spectra were more conservative in certain building locations, while in others, they provided similar or lower values, suggesting potential cost savings in design. The FIS model demonstrates its efficacy in producing more accurate and robust designs by considering the uncertainties inherent in the problem. Furthermore, this approach has the potential to be extended to study seismic parameters of other design codes, although further research is required to comprehensively explore its capabilities and limitations.

Human Sitting Postures Classification Based on Angular Features with Fuzzy-Logic Labeling

Musculoskeletal disorders (MSDs) are generally associated with sitting postures. Assessing and ensuring healthy sitting posture are indispensable aspects of reducing the occurrence of MSDs. This study aims to develop a system that allows office workers' body postures to be contactless and recognized by different classification methods while sitting on a chair and can be used for health applications. Five different sitting body postures have been determined within the scope of medical and health literature studies and relevant standards. Thirty subjects were asked to sit in these body postures for 30 seconds. While the subjects were sitting, skeleton point position defined as a pose data of the subjects were obtained from the Kinect device simultaneously. Five angles that are thought to distinguish sitting positions according to different joint positions were determined and calculated. The angle values that can take in the standard sitting position in the literature have been determined. According to these values, the angle values in other postures were determined. A rule-based fuzzy inference system was designed using angle values for labeling sitting posture data. Angle values were calculated to classify the labeled depth values, and an artificial neural network classifier was designed according to these angle values. As a result, five different sitting body postures were classified with KNN (K-Nearest Neighbours) and Neural Network (NN), respectively, with 98.9% and 97% overall accuracy values. The study was compared with other studies in the literature. In this context, a high-performance system design that can improve healthy sitting behaviors for office workers that can be used in both health applications and robot vision is presented.

Rule-based fuzzy inference system for landslide susceptibility mapping along national highway 7 in Garhwal Himalayas, India

The Mountainous terrain,in the Himalayas is experiencing rapid development in a bewildering manner, which makes it more susceptible to landslides. Management and mitigation of landslide hazard begin with its mapping by integrating numerous methods and Geographic Information System (GIS) tools. However, it is difficult to produce reliable landslide susceptibility maps (LSM) with traditional remote sensing and GIS methods due to complexity of the mountainous terrain environments and huge datasets. Therefore, the present study investigates the applicability of Mamdani’s fuzzy inference system (FIS) to produce LSM in Himalayan terrain in India. It is compared with commonly used frequency ratio (FR) and information value method (IVM) approaches. Several causative factors were extracted and used to prepare thematic layers, including slope, aspect, curvature, solar radiance, SPI, TWI, rainfall, soil depth and NDVI. Landslide inventory was also created using google earth images and previously published work. The accuracy estimates for FR, IVM and FIS were performed based on ROC curves. FIS was found to provide an accuracy of 77.7%, followed by IVM (72%) and FR (71%) for LSM. The current study is a prototype for further studies in the Garhwal Himalayas and similar terrains, based on the vigorous Mamdani’s techniques of fuzzy inference theory. The outcomes of this work propose that an expert’s knowledge-based FIS method can produce an accurate LSM in such a complex terrain. Planners and concerned authorities can use the results further for landslide management and mitigation.

A novel PID controller for pressure control of artificial ventilator using optimal rule based fuzzy inference system with RCTO algorithm

In order to improve the pressure tracking response of an artificial ventilator system, a novel proportional integral derivative (PID) controller is designed in the present work by utilizing an optimal rule-based fuzzy inference system (FIS) with a reshaped class-topper optimization algorithm (RCTO), which is named as (Fuzzy-PID). Firstly, a patient-hose blower-driven artificial ventilator model is considered, and the transfer function model is established. The ventilator is assumed to operate in pressure control mode. Then, a fuzzy-PID control structure is formulated such that the error and change in error between the desired airway pressure and actual airway pressure of the ventilator are set as inputs to the FIS. The gains of the PID controller (proportional gain, derivative gain, and integral gain) are set as outputs of the FIS. A reshaped class topper optimization algorithm (RCTO) is developed to optimize rules of the FIS to establish optimal coordination among the input and output variables of the FIS. Finally, the optimized Fuzzy-PID controller is examined for the ventilator under different scenarios such as parametric uncertainties, external disturbances, sensor noise, and a time-varying breathing pattern. In addition, the stability analysis of the system is carried out using the Nyquist stability method, and the sensitivity of the optimal Fuzzy-PID is examined for different blower parameters. The simulation results showed satisfactory results in terms of peak time, overshoot, and settling time for all cases, which were also compared with existing results. It is observed in the simulation results that the overshoot in the pressure profile is improved by 16% with the proposed optimal rule based fuzzy-PID as compared with randomly selected rules for the system. Settling time and peak time are also improved 60–80% compared to the existing method. The control signal generated by the proposed controller is also improved in magnitude by 80–90% compared to the existing method. With a lower magnitude, the control signal can also avoid actuator saturation problems.

Smart City Transformation: An Analysis of Dhaka and Its Challenges and Opportunities

Cities worldwide are experiencing rapid urbanization and an increasing population, creating a pressing need for smart infrastructure to enhance citizen services. Dhaka, the capital of Bangladesh, faces similar technological and socio-economic challenges, making it crucial to transform it into a sustainable smart city. This research analyzes the opportunities and challenges of smart cities and Dhaka through SWOT and PESTEL analyses. The study employs a fuzzy rule-based inference system in a MATLAB simulation to calculate the smart city index based on parameters such as governance, transportation, waste management, utility management, healthcare, and industrial automation. The findings reveal that good governance has the highest impact on the smart city index, followed by transportation. The paper proposes a sustainable smart city transportation framework and management technique, outlining future research directions. The proposed framework is expected to impact socio-economic, technological, and environmental aspects positively.

W-Infer-polation: Approximate reasoning via integrating weighted fuzzy rule inference and interpolation

Fuzzy rule-based inference systems facilitate approximate reasoning for decision-making under circumstances where knowledge is imprecisely characterised. Compositional rule of inference (CRI) and fuzzy rule interpolation (FRI) are two typical types of technique to implement fuzzy systems. Questions of when to apply which of these two fuzzy inference techniques is often addressed by checking whether there exist certain rules that can match given observations. Both techniques have been widely investigated to improve the performance of approximate reasoning, with increasingly more attention being paid to the development of systems where rule antecedent attributes are associated with measures of their relative significance or weights. Unfortunately, they are mostly done in a separate manner within their own fields, making it difficult to achieve accurate reasoning when both techniques are required simultaneously. This paper presents an innovative fuzzy inference mechanism, W-Infer-polation, which organically integrates both enhanced versions of CRI and FRI that are equipped with rule attribute weights. In particular, the individual weights of rule antecedents and consequent are generated using the given unweighted rules only, creating an attribute weighted rule base. From this, W-Infer-polation exploits the learned weights to guide the selection of weighted rules for rule firing in CRI and that of nearest weighted rules for FRI. A systematic comparative experimentation is also presented, demonstrating the efficacy of W-Infer-polation.

Design of an optimized fuzzy system for edge detection in images

Edge Detection is the first stage in the image division into separate parts. Image division is the partitioning of a digital image to the different zones or the set of pixels. Edge detection is one of the techniques applied in digital image processing often. The purpose of detecting pixels is to match the edges in the image. Filtering, Enhancement, and Detection are three steps in edge detection. Images are usually destroyed by casual changes in intensity intervals called noise or confusion. some noise variations include salt and pepper, pulse, and Gaussian. However, there is a relation between edge detection power and noise reduction. Using filters to the noise reduction causes the loss of edge detection power. For facilitating the edges detection, it is essential for the determination of pixels’ intensity constraints in their neighborhood. Many points in an image have a nontransparent slope, and all of them are not the edges of the joint space. Therefore, some of the linear and nonlinear methods such as Sobel, Prewitt, and Robert have to be used to determine the edge points. The fuzzy logic and the system based on it, is one of the most effective methods for edge detection. This paper presents an optimized rule-based fuzzy inference system and designs the efficiency mask matric. The simulation results for edge detection are presented using the traditional edge detection techniques, including Binary Filter, Sobel Filter, Prewitt Filter, and Robert Filter. Also, it is presented using the fuzzy approach. The simulation results show that the designed fuzzy system has been able to detect the edges of the image more accurately and help to increase the sharpness and quality of the edges. Therefore, the proposed method has more accurate and more reliable results and reduces false edge detection comparison to the traditional methods.

MATHEMATICAL MODELING FOR RAINFALLPREDICTION THROUGH RULE BASE FUZZY INFERENCE SYSTEM USING MATLAB: A CASE STUDY IN RAIPUR DISTRICT (CHHATTISGARH STATE)

In human life, Weather forecasting is a very important and required field because in our country maximum people depend upon agriculture. The agricultural economy is largely based upon irrigation and rainfall. For analyzing the productivity of crops rainfall prediction is required and necessary for all farmers. In the present work, we use a rule-based fuzzy inference system (FIS) is employed to forecast day-wise concentrations in the ruler area of the Raipur district. This forecasting model was developed by using the 2 year period July 2016 and July 2017 and the evaluation of the model was achieved through a series of well-established evaluation parameters and methodologies. The evaluation reveals that the FIS models give the best forecasting values of approximately 87 to 88 percent. This will be more accurate as compared to the previous models. For a generation model, we take five parameters: Average temperature, wind direction, pressure, entire cloud cover, and corresponding humidity are the input variable for our model, each parameter consist of three membership functions. The data is used two years metrological data of the rural area of Raipur district (Chhattisgarh state). Our model is based on thirty-two If-Then rules and fuzzy reasoning. The output variable has three membership functions (Light, Medium, and Heavy Rainfall) which are assigned as (0 - 100) percentages for rainfall prediction given in day-wise. The result is in high concurrence, with the actual data.

A fuzzy-based flood warning system using 19-year remote sensing time series data in the Google Earth Engine cloud platform

Many Flood Warning Systems (FWS) have been developed to date to reduce flood risk and properly manage this natural disaster. This study presents a novel method to create an FWS based on anomaly detection in remote sensing climate data from western Lorestan, Iran, from 2001-to 2019. To this end, the monthly time series of climate products related to floods (e.g., precipitation, soil moisture, soil and air temperatures, vegetation, snow, and evapotranspiration) were first processed in Google Earth Engine (GEE). Then, three algorithms – Median-Interquartile range (M−IQR), Multi-Layer Perceptron (MLP), and Recurrent Neural Network (RNN) – were applied to detect anomalies in the time series of each parameter. Finally, a rule-based Fuzzy Inference System (FIS) was designed to estimate the potential of floods per month by establishing the relationship between the observed anomalies and the occurrence of floods. The results of the proposed Fuzzy-based Flood Warning System (FFWS) using all three anomaly detection methods accurately showed the very high potential for floods in March and April 2019 (i.e., actual flood events). Two other floods occurred in October 2015 and April 2016 were also considered for further evaluation of the proposed method. The results indicated that the RNN method achieved the highest performance in flood forecasting with the overall accuracy and Kappa coefficient of 93.85% and 0.93, respectively. Moreover, the potential of floods at the beginning of 2019 (i.e., January and February) was also high, although not to the extent as in March and April, indicating that the proposed method correctly identified the potential of flooding in later months and can thus provide a warning to help mitigate the impact of flood damage.

Novel Method for Safeguarding Personal Health Record in Cloud Connection Using Deep Learning Models.

It is a new online service paradigm that allows consumers to exchange their health data. Health information management software allows individuals to control and share their health data with other users and healthcare experts. Patient health records (PHR) may be intelligently examined to predict patient criticality in healthcare systems. Unauthorized access, privacy, security, key management, and increased keyword query search time all occur when personal health records (PHR) are moved to a third-party semitrusted server. This paper presents security measures for cloud-based personal health records (PHR). The cost of keeping health records on a hospital server grows. This is particularly true in healthcare. As a consequence, keeping PHRs in the cloud helps healthcare institutions save money on infrastructure. The proposed security solutions include an optimized rule-based fuzzy inference system (ORFIS) to determine the patient's criticality. Patients are classified into three groups (sometimes known as protective rings) based on their severity: very critical, less critical, and normal. In trials using the UCI machine learning archive, the new ORFIS outperformed existing fuzzy inference approaches in detecting the criticality of PHR. Using a graph-based access policy and anonymous authentication with a NoSQL database in a private cloud environment improves data storage and retrieval efficiency, granularity of data access, and response time.

A Review on the Rule-Based Filtering Structure with Applications on Computational Biomedical Images.

In this paper, we present rule-based fuzzy inference systems that consist of a series of mathematical representations based on fuzzy concepts in the filtering structure. It is crucial for understanding and discussing different principles associated with fuzzy filter design procedures. A number of typical fuzzy multichannel filtering approaches are provided in order to clarify the different fuzzy filter designs and compare different algorithms. In particular, in most practical applications (i.e., biomedical image analysis), the emphasis is placed primarily on fuzzy filtering algorithms, with the main advantages of restoration of corrupted medical images and the interpretation capability, along with the capability of edge preservation and relevant image information for accurate diagnosis of diseases.

Fuzzy inference systems for mineral prospectivity modeling-optimized using Monte Carlo simulations

This paper uses Monte Carlo simulations to estimate the parameters of rule-based fuzzy inference systems (FISs) designed for mineral prospectivity modeling. The targeted process for the case study is gold mineralization in the Rajapalot project area in northern Finland. Mamdani-type FISs are developed and implemented for the predictive modeling of favorable structural settings and favorable chemical traps causing gold enrichment in host rocks from ore-bearing hydrothermal fluids. The parameters of the fuzzification functions control the output fuzzy membership values. Traditionally these parameters are chosen subjectively based on the expert's domain knowledge. This study uses drill core data statistics to define the distribution of the parameters. Subsequently, Monte Carlo simulations are used to simulate the corresponding fuzzy membership values and optimize the FISs.•Capturing the complexities of the multi-processes geodynamic systems and the possible interplay mineralization-related geological aspects using ‘If-Then’ rule-based fuzzy inference systems.•Implementation of Monte Carlo simulations for quantification of uncertainties related to a Mamdani-type FIS-based prospectivity modeling.•Reporting prospectivity modeling results at different confidence levels for informed decision making on selection of exploration targets.

Recovering Missing Data via Top-k Repeated Patterns for Fuzzy-Based Abnormal Node Detection in Sensor Networks

The stream data acquired by heterogeneous Internet of Things (IoT) sensors are seldom perfect. Most of the collected data streams include either missing or abnormal values caused by various factors such as failure, malfunction, or integrity attacks. Such unreliable data affect the real-time monitoring and compromise the quality of data analysis. By simply analyzing the sensor data via anomaly detection, applications may still be unreliable over the incomplete sensor data streams. Therefore, a reliable method for recovering the missing data and detecting the abnormal ones is indispensable in the IoT environment. This paper presents FuzHD++, a new method to recover missing sensor data and detect abnormal nodes jointly rather than independently. Both elements, data recovery and abnormal node detection, rely on the observed temporal and spatial correlation of sensor data to effectively achieve reliable recovery estimation and detection performance. In the data recovery process, the system adopts a matrix profile to extract the top-<i>k</i> repeated patterns from different sensor nodes. Furthermore, it utilizes the <i>k</i>-nearest neighbor estimator to recover the missing data based on the extracted pattern information of multiple neighbor nodes. During the abnormal node detection process, the system adopts a refined fuzzy rule-based detection method. The refined fuzzy rule-based inference system integrates the expert rules and the rules obtained from sensor data analysis to treat the ambiguity in the decision-making process. We validated the performance of FuzHD++ by comparing it with existing methods using two real-world datasets. Our results showed that the proposed missing sensor data recovery method achieves more than 20% improved root mean square error results than most existing methods. Furthermore, FuzHD++ achieved an average accuracy of 92% for analyzing the sensor readings and detecting the abnormal ones. According to the results, the proposed mechanisms based on the observed temporal and spatial correlation analysis improve the robustness of IoT against data loss and integrity attacks.

Prioritization of risks related to BIM implementation in brazilian public agencies using fuzzy logic

BIM (Building Information Modeling) is a disruptive technology that has changed the AEC industry (Architecture, Engineering and Construction) scenario, which has been growing worldwide, generating very effective solutions for the sector. In Brazil, this growth has been driven mainly by government actions through decrees and measures aimed at spreading BIM throughout the national territory. Thus, the market share that has not yet implemented this process is in a hurry to do so, and it is exactly at this point that many professionals, companies and agencies make mistakes, as they implement other processes without knowing its bases and prescriptions. It is in this context that carrying out studies such as this one becomes necessary. The main goal of this work is to generate a prioritization list of the main risks associated to BIM implementation in Brazilian public agencies. Such prioritization is based on the literature, on account of it seeking the most representative risks in the international context through a systematic mapping of the literature. These risks are submitted to a team involved with implementation processes in a representative body responsible for implementing this process in Brazil. Thus, a risk characterization is generated according to two aspects: likelihood of occurrence and impact. These data are submitted to the fuzzy rule-based inference system. Hence, through fuzzy logic, the list of prioritizations of the main risks linked to BIM adoption in the context of public agencies is generated. Using fuzzy modeling through subsystems to assess the criticality of risks related to BIM implementation is considered an innovation, which marks the originality of this article. The first three risks of the generated prioritization list are inadequate relevant knowledge and experience, interoperability issues and cultural resistance, all strongly interconnected. As a scientific contribution, this study demonstrates the themes to be initially solved in the Brazilian context for the elimination of its main obstacles. It also serves as a reference to countries that are in the same stage and context of implementation. Data like this tend to scientifically support the AEC industry and make BIM development, combined with public policies, able to reach maturity levels already presented by developed countries.

An integrated approach of fuzzy risk assessment model and data envelopment analysis for route selection in multimodal transportation networks

The main objective of this study is to first propose a novel integrated framework of fuzzy risk assessment model (FRAM), data envelopment analysis (DEA), and multiple criteria decision-making (MCDM) approaches for route selection in multimodal transportation networks. In the FRAM phase, the magnitude calculation of risks was operated by decision makers, who can provide their opinions on the probability of occurrence and severity of consequences through linguistic variables and triangular fuzzy numbers for risk likelihood and severity scales. The Mamdani fuzzy rule-based inference system including the rule’s firing strengths is established to convert the membership degrees for each term of aggregated likelihood and severity scales into those for each term of the risk magnitude scale. In the DEA phase, precise and crisp risk magnitudes are characterized by a new defuzzifier based on the DEA algorithm, which is applied instead of classical defuzzification methods. The three decision criteria of transportation cost, transportation time, and overall risk magnitude are weighted by a fuzzy analytic hierarchy process and then investigated based on the consensus of decision makers’ needs by a zero-one goal programming model, which is used to select the most appropriate multimodal route. Finally, the integrated approach is tested to reveal its capability and aptness using a real-world multimodal freight transportation route selection between Thailand and Cambodia. The proposed framework contributes to an easy-to-apply technique for risk predictability in multimodal transportation networks and provides powerful decision-making for the effective selection of the most appropriate alternative under the fuzzy context.

Development of a decision support system for assessing the supply chain risk mitigation strategies: an application in Indian petroleum supply chain

PurposeThe purpose of this paper is to develop a decision support system (DSS) to assist supply chain (SC) risk managers to select a suitable risk management (RM) strategy and expedite the implementation of corresponding RM enablers. The relationship between RM strategies and RM enablers is explored by identifying the underlying factors between them, which is further used to build the DSS.Design/methodology/approachThe DSS is built by integrating heterogeneous techniques. A systematic review approach is employed to explore both proactive and reactive RM enablers, and they are further mapped to various RM strategies by using correspondence analysis (CA). An in-depth interview is conducted to develop the rules for constructing the decision system. A rule-based fuzzy inference system (FIS) is utilized to counteract the uncertainty involved in the decision variables. The efficacy of the proposed DSS is demonstrated by considering two conjectural scenarios in the case of Indian petroleum SC (IPSC).FindingsThe results reveal three primary underlying factors between the risk mitigation strategies viz. SC managers' preparedness to face risk, organization's resource capability to deal with risk and the sophistication of the implementation of the RM enablers; with explained variances of 37%, 29% and 22%, respectively. Risk avoidance strategy comprises of RM enablers such as supplier evaluation, technology adaption, information security, etc. Whereas, the risk-sharing strategy includes revenue sharing, insurance, collaboration, public-private-partnership, etc. as essential RM enablers. The DSS recommends risk-mitigation and risk-sharing as effective RM strategies for the IPSC under the considered scenarios.Research limitations/implicationsThis paper develops a decision support framework for recommending an effective risk mitigation strategy and outranking the corresponding enablers. The study explicitly focuses on the risk mitigation step of the supply chain risk management (SCRM) process. Pre- and post-risk mitigation steps of the SCRM process, such as risk assessment and risk monitoring are beyond the scope of this research.Originality/valueThe operational procedure of the proposed DSS is explained by considering a real-life case of petroleum SC in the Indian scenario. The unique contributions of this study are presented as theoretical implications and managerial propositions in the context of a developing country.

Adaptive neuro-fuzzy approach for prediction of dewpoint pressure for gas condensate reservoirs

Dewpoint pressure is an important parameter for reservoir management and characterization. Gas condensate reservoirs experience significant reduction in productivity when initial reservoir pressure decreases below the dewpoint pressure. As such, an effective and efficient methods for prediction of this thermodynamic quantity are crucial for operational plans. In this article, a hybrid artificial intelligence model, based on adaptive neuro-fuzzy approach, for the prediction of gas condensate dewpoint pressure is presented. The proposed model combines the learning ability of artificial neural network and the capability of rule-based fuzzy inference system. First, fuzzy subtractive clustering technique is applied to a set of measured input/output data to identify an initial system based on extracted set of rules. The generated system is then trained using adaptive neuro-fuzzy inference system after which model validation and testing were performed. The performance of the proposed model is compared with existing methods. The results show that our proposed model outperforms the previous and existing methods with 99% accuracy and with the least root mean square error of 2.188 for some selected fluid sample.

Curvature-based sparse rule base generation for fuzzy rule interpolation

Fuzzy logic has been successfully widely utilised in many real-world applications. The most common application of fuzzy logic is the rule-based fuzzy inference system, which is composed of mainly two parts including an inference engine and a fuzzy rule base. Conventional fuzzy inference systems always require a rule base that fully covers the entire problem domain (i.e., a dense rule base). Fuzzy rule interpolation (FRI) makes inference possible with sparse rule bases which may not cover some parts of the problem domain (i.e., a sparse rule base). In addition to extending the applicability of fuzzy inference systems, fuzzy interpolation can also be used to reduce system complexity for over-complex fuzzy inference systems. There are typically two methods to generate fuzzy rule bases, i.e., the knowledge driven and data-driven approaches. Almost all of these approaches only target dense rule bases for conventional fuzzy inference systems. The knowledge-driven methods may be negatively affected by the limited availability of expert knowledge and expert knowledge may be subjective, whilst redundancy often exists in fuzzy rule-based models that are acquired from numerical data. Note that various rule base reduction approaches have been proposed, but they are all based on certain similarity measures and are likely to cause performance deterioration along with the size reduction. This project, for the first time, innovatively applies curvature values to distinguish important features and instances in a dataset, to support the construction of a neat and concise sparse rule base for fuzzy rule interpolation. In addition to working in a three-dimensional problem space, the work also extends the natural three-dimensional curvature calculation to problems with high dimensions, which greatly broadens the applicability of the proposed approach. As a result, the proposed approach alleviates the ‘curse of dimensionality’ and helps to reduce the computational cost for fuzzy inference systems. The proposed approach has been validated and evaluated by three real-world applications. The experimental results demonstrate that the proposed approach is able to generate sparse rule bases with less rules but resulting in better performance, which confirms the power of the proposed system. In addition to fuzzy rule interpolation, the proposed curvature-based approach can also be readily used as a general feature selection tool to work with other machine learning approaches, such as classifiers.