Rule Extraction Research Articles

Separate-and-conquer survival action rule learning

Action mining is a data mining method that aims to identify recommendations for changing attribute values that can lead to the classification of data instances as examples of another class. Action mining algorithms extract rules containing recommendations in the premises and class changes in the conclusion. To the best of the authors’ knowledge, no method has been proposed yet for generating action rules based on censored data. This study introduces the first method for survival action rule generation. The method stems from the covering rule induction algorithm but generates rules defining the actions required to change not the class but the survival curve of the covered examples. Thus, this study poses a new research problem: generating action rules for censored data and survival analysis. This study evaluated the proposed method using 22 data sets in which two application domains of survival analysis were distinguished: medicine and predictive maintenance. In addition, more detailed analyses of the generated survival action rules were presented in the form of case studies for the two selected data sets. The results show that the proposed method generates good-quality survival action rules and changes in the survival curves, resulting from the identified actions are significant.

Decision-making method for high-speed rail early warning system in complex earthquake situations

Abstract To address the shortcomings in decision-making methods for ground motion threshold warning models in high-speed rail earthquake early warning systems (HSREEWs), we propose a dual judgement method and corresponding early warning process for earthquake early warning decisions based on joint peak ground acceleration (PGA) and complex earthquake environmental risk evaluation (ERE) values. First, we analyse the characteristics of four complex earthquake environments based on the characteristics of high-speed rail (HSR) operating environments. Second, we establish an earthquake environmental risk evaluation index system and propose an adversarial interpretive structure modelling method-based complex earthquake situation evaluation model (AISM-based ESEM). The AISM method firstly evaluates the proximity by the TOPSIS (technique for order preference by similarity to an ideal solution) method, then effectively rank targets with fuzzy attributes through opposite hierarchical extraction rules without sacrificing system functionality. Since PGA can reflect the current size of earthquake energy, combining PGA thresholds with ESEM-derived values of ERE can effectively determine the risk status of each train and make decisions on the most appropriate alarm form and control measures for that status. Finally, case analysis results under the background of Wenchuan Earthquake show that the new early warning decision-making method accurately assesses environmental risks in affected areas and provides corresponding warning levels as a supplement to existing HSREEWs warning models.

Fuzzy Rule-Based Explainer Systems for Deep Neural Networks: From Local Explainability to Global Understanding

Explainability of deep neural networks has been receiving increasing attention with regard to auditability and trustworthiness purposes. Of the various post-hoc explainability approaches, rule extraction methods assist to understand the logic that underpins their functioning. Whereas the rule-based solutions are directly managed and understood by practitioners, the use of intervals or crisp values in the antecedents that rely on numerical values might not be intuitive enough. In this case, the benefits of a linguistic representation based on fuzzy sets/rules are straightforward, as these semantically meaningful components ease the model understanding. This paper proposes fuzzy rule-based explainer systems for deep neural networks. The algorithm learns a compact yet accurate set of fuzzy rules based on features' importance (i.e., attribution values) distilled from the trained networks. These systems can be used for both local and global explainability purposes. The evaluation results of different applications revealed that the fuzzy explainers maintained the fidelity and accuracy of the original deep neural networks while implying lower complexity and better comprehensibility.

Optimization-informed Rule Extraction for HVAC system: A Case Study of Dedicated Outdoor Air System Control in a Mixed-Humid Climate Zone.

In the era of post-Coronavirus Disease 2019, the dedicated outdoor air system (DOAS), which provides 100% outdoor air for the building, is widely acknowledged as it can ensure acceptable indoor air quality by delivering fresh outdoor air to occupied space. The DOAS with a proper design and operation can provide sufficient ventilation and dehumidification while achieving energy efficiency. Nonetheless, there is limited guidance in determining the optimal control sequence of the DOAS for the designers and operators to implement in practice. Accordingly, in practice, a number of issues have been acknowledged in the design and control phases of DOAS, including insufficient ventilation and dehumidification, and increasing supply air dry-bulb temperature in fear of over-cooling, which might cause significant discomfort and energy waste. There have been efforts to develop high-performing DOAS controls for better energy efficiency. However, such controls are often complex, or difficult to interpret, for building designers and operators to consider in practice. In this regard, this paper explores a simulation-based framework for generating a supply air temperature control sequence of the DOAS not only to ensure improved energy-saving potential but also to guarantee the implement-ability of the control logic. The U.S Department of Energy prototype primary school with dynamic occupancy profiles was modeled with a whole building simulation program, EnergyPlus. The model consists of a DOAS with an exhaust air energy recovery system for ventilation and fan-coil units for space cooling and heating. Then, a Genetic Algorithm was adopted to find the true optimal supply air temperature control sequence in terms of minimizing the energy cost of the heating, ventilation, and air conditioning system operation. Lastly, Decision Tree was adopted to extract rules out of the optimums to derive an implementable sequence of operation for the DOAS supply air temperature. A total of 12 week-simulation including four weeks of heating, cooling, and shoulder seasons, separately, under the weather condition of New York City was conducted for the case study. This case study identified that the optimization-informed rule extraction-based control, when compared to conventional outdoor air temperature-based reset control, could save about 13% of energy cost and 25% of energy consumption throughout the heating, cooling, and shoulder seasons. It is notable that the energy-saving was mainly achieved by reducing the heating energy consumption. Importantly, it nearly corresponds to the true optimal control result, which reduces approximately 14% of energy cost and 27% of energy consumption. From the results, it can be highlighted that the optimization-informed rule extraction can be as energy effective as the optimal control, while significantly reducing the complexity of the control.

A hybrid association analysis framework of accident reports for offshore drilling platforms

As the key work unit of offshore oil and gas exploration and exploitation activities, an offshore drilling platform (ODP) integrates high-density equipment and facilities in a relatively narrow area, making it prone to frequent serious accidents under the influence of environmental factors. The mining association rules of the hidden dangers from the accumulated historical accident reports can help find the potential causes of the risks and proactively reduce the risk of accidents and damages. However, due to the professionalism of the corpus linguistics of the offshore oil and gas industry and the complex correlations between multiple named entities, mining valuable information from massive transaction datasets has increasingly become a challenge for academia and industry. To this end, a hybrid association analysis framework for ODPs is proposed in this paper, which is divided into four stages: data preprocessing, information extraction, association rule mining and making a rectification plan. In the key information extraction stage, we propose a three-layer deep learning network based on the BERT-IDCNN-BiLSTM-CRF (BIBC) model, which makes effective use of the semantic information of the context to extract the trituples of the hidden dangers (i.e., equipment, location and phenomenon). Based on the extracted entities, an effective multientity association rule mining algorithm based on hash technology and an inverted itemset (HTApriori) as a variant of Apriori for ODP databases is developed to understand the many-to-one, one-to-many and many-to-many risky causes between the entities. A series of real-world experimental results show that the proposed framework offers more reliable and effective performances of information extraction and association rule mining than the comparison methods. By analyzing the association results, the hidden dangers and their association rules, which occur with some small probability but are critical in ODPs, can be found. This work is helpful in significantly improving the rationality of the rectification plans. In addition, the application results on the CoNLL2003 dataset further prove the generalization performance of the proposed method.

Predicting post–liver transplant outcomes in patients with acute-on-chronic liver failure using Expert-Augmented Machine Learning

Liver transplantation (LT) is a treatment for acute-on-chronic liver failure (ACLF), but high post-LT mortality has been reported. Existing post-LT models in ACLF have been limited. We developed an Expert-Augmented Machine Learning (EAML) model to predict post-LT outcomes. We identified ACLF patients who underwent LT in the University of California Health Data Warehouse. We applied the RuleFit machine learning (ML) algorithm to extract rules from decision trees and create intermediate models. We asked human experts to rate the rules generated by RuleFit and incorporated these ratings to generate final EAML models. We identified 1384 ACLF patients. For death at 1 year, areas under the receiver-operating characteristic curve were 0.707 (confidence interval [CI] 0.625-0.793) for EAML and 0.719 (CI 0.640-0.800) for RuleFit. For death at 90 days, areas under the receiver-operating characteristic curve were 0.678 (CI 0.581-0.776) for EAML and 0.707 (CI 0.615-0.800) for RuleFit. In pairwise comparisons, both EAML and RuleFit models outperformed cross-sectional models. Significant discrepancies between experts and ML occurred in rankings of biomarkers used in clinical practice. EAML may serve as a method for ML-guided hypothesis generation in further ACLF research.

EVaDe: Efficient and Lightweight Mirai Variants Detection via Approximate Largest Submatrix Search

The Mirai botnet, notorious for launching significant Distributed Denial of Service (DDoS) attacks and crippling portions of internet services in late 2016, has emerged as a significant threat. Its threat is magnified by the open-source nature of the original Mirai code, which enables a propagation and evolution rate that surpasses traditional malware and frequently defies common sense. As the primary targets of Mirai attacks, Internet of Things (IoT) devices must promptly adapt to the evolving variations of the Mirai threat scenario. In practice, however, IoT devices are frequently constrained by insufficient security detection resources. Therefore, there is an urgent need for a lightweight framework capable of handling Mirai variants and dynamically updating its rule set in order to effectively counter the threat. In response to these challenges, we present Efficient and lightweight Mirai Variants Detection (EVaDe), a novel, lightweight framework for detecting Mirai. EVaDe unleashes the power of sample function mining to efficiently automate the generation of detection rules, requiring limited hardware resources while maintaining effectiveness against Mirai and its numerous variants. In addition, to improve the efficacy of rule generation, we propose a sophisticated algorithm designed to optimize the maximum submatrix problem, thereby facilitating the efficient and rapid extraction of malicious rules from the sample group. We validated the experiments on actual IoT devices with significantly compressed performance overheads. An average sample detection time of 5 ms to make sure the system can be deployed in real production. According to the result, the approach has an average detection rate of 95% for Mirai and its variants, which beats every other well-known piece of commercial antivirus software on the market by 3% to 56%.

Strong collaborative governance networks support effective Forest Stewardship Council-certified community-based forest management: Evidence from Southeast Tanzania

Research on community-based forest management indicates its conservation outcomes depend on local rule enforcement, extraction pressures, and community support. However, many community-based forest management projects, particularly in the Global South, also involve collaborative networks of non-state actors such as NGOs and private corporations. Many of these networks promote sustainability certification under programs like the Forest Stewardship Council. We report on analyses of longitudinal forest cover data constructed using satellite observations alongside inter-organizational collaborative governance network data constructed from archival sources, document analysis, and oral histories to assess how collaborative governance networks shape community-based forestry’s conservation effectiveness in eight villages in Kilwa District, Tanzania. Our findings indicate certified community-based forestry’s impacts on deforestation can depend on the composition and structure of collaborative governance networks. Using matched Cox proportional hazards models with geographic fixed effects, we find evidence that certified community-based forest management can stem forest loss as effectively as state-led forest management (in the form of National Forest Reserves). However, the characteristics of collaborative governance networks connecting organizations engaged in forest management in our study villages shape both which areas are selected into certified community-based forest management and villages’ overall deforestation rates. Specifically, we find that the more each village government’s organizational partners are connected to one another through bonding ties, and the more civil society organizations collaborate with each village government through bridging ties, the lower the village’s deforestation risk. More private sector organizations connected to village governments through bridging ties, however, are associated with higher deforestation risks. Our evidence highlights the importance of investments in inter-organizational networks for promoting sustainably certified community-based forest conservation.

Developed ABCLASS-Miner Classification Algorithm Based Rule Extraction for Denim Fabrics

Obtaining and storing large amounts of data have become easier with the rapidly developing information technologies (IT). However, the data generated and collected, which are irrelevant in and of themselves, become useful only when they are analyzed for a specific reason. Data mining may transform raw data into useful information. In the present study, classification and analysis of denim fabric quality characteristics according to denim fabric production parameters were carried out. The present study proposes a new classification rule inference algorithm. The suggested approach is mostly based on Artificial Bee Colony Optimization (ABC), a swarm intelligence meta-heuristic. In each step of the algorithm, there are two phases called the employed bee phase and the onlooker bee phase. This algorithm has been compared with the classification algorithms in the related literature. This proposed algorithm is a new data mining tool that intelligently combines various metaheuristic and neural networks and can generate classification rules. The results indicate that the proposed data mining algorithms may be highly useful in determining weight and width in denim fabric manufacture.

REUSE OF INFORMATION BASED ON THE INTERPRETATION OF KNOWLEDGE

Recently, much attention has been paid to the creation of knowledge bases that contain millions of facts about various objects of the real world. One of the key aspects of knowledge management is the reuse of previously acquired knowledge. The subject of research is the processes of knowledge reuse and the creation of software systems based on knowledge bases. Knowledge interpretation is one approach to knowledge reuse, which consists in deriving new knowledge based on existing facts in the knowledge base. The purpose of the study is to increase the efficiency of knowledge reuse in software systems based on knowledge bases due to automatic rule extraction. To achieve the goal, the following tasks were solved: approaches to structuring the facts available in the database were considered, a qualitative analysis of the possibility of applying automatic methods of rule construction and derivation was carried out. The task of predicting the connection between a pair of entities, which determines the presence of a relationship for facts, is considered. A generalized approach to the presentation of facts is proposed, which allows the use of efficient rule-finding algorithms. The following methods are used to solve the given problem: the algebra of finite predicates and predicate operations for knowledge representation, methods for predicting the connection between a pair of entities based on representative learning for automatically obtaining rules. The following results were obtained: an approach to rule formation was considered, which allows structuring existing facts as a set of binary predicates and applying automatic methods of rule construction and derivation. It is concluded that the limitation of knowledge reuse is the structure of the knowledge base and the software used to support it. The article formulates the principles of building specific concentrator predicates for the representation of attributes, which allows generalizing the predicate representation of facts and applying automatic methods of rule extraction, which increases the efficiency of knowledge reuse. Conclusions: the application of the method and mechanism of identification based on predicate operations and specific predicates, which automatically extracts attributes from the knowledge base, together with the quality assessment of the derived rules, made it possible to propose a generalized approach for presenting facts and use effective rule search algorithms, which allows to increase the efficiency of reuse knowledge in software systems.

The Design of a Dynamic Configurable Packet Parser Based on FPGA.

To meet the evolving demands of programmable networks and address the limitations of traditional fixed-type protocol parsers, we propose a dynamic and configurable low-latency parser implemented on an FPGA. The architecture consists of three protocol analysis modules and a TCAM-SRAM. Latency is reduced by optimizing the state machine and parallel extraction matching. At the same time, we introduce the chain mapping idea and container concept to formulate the matching and extraction rules of table entries and enhance the extensibility of the parser. Furthermore, our system supports dynamic configuration through SDN control, allowing flexible adaptation to diverse scenarios. Our design has been verified and simulated with a cocotb-based framework. The resulting architecture is implemented on Xilinx Ultrascale+ FPGAs and supports a throughput of more than 80 Gbps, with a maximum latency of only 36 nanoseconds for L4 protocol parsing.

Factors influencing initial public acceptance of integrating the ChatGPT-type model with government services

PurposeIntegrating the Chat Generative Pre-Trained Transformer-type (ChatGPT-type) model with government services has great development prospects. Applying this model improves service efficiency but has certain risks, thus having a dual impact on the public. For a responsible and democratic government, it is necessary to fully understand the factors influencing public acceptance and their causal relationships to truly encourage the public to accept and use government ChatGPT-type services.Design/methodology/approachThis study used the Latent Dirichlet allocation (LDA) model to analyze comment texts and summarize 15 factors that affect public acceptance. Multiple-related matrices were established using the grey decision-making trial and evaluation laboratory (grey-DEMATEL) method to reveal causal relationships among factors. From the two opposite extraction rules of result priority and cause priority, the authors obtained an antagonistic topological model with comprehensive influence values using the total adversarial interpretive structure model (TAISM).FindingsFifteen factors were categorized in terms of cause and effect, and the antagonistic topological model with comprehensive influence values was also analyzed. The analysis showed that perceived risk, trust and meeting demand were the three most critical factors of public acceptance. Meanwhile, perceived risk and trust directly affected public acceptance and were affected by other factors. Supervision and accountability had the highest driving power and acted as the causal factor to influence other factors.Originality/valueThis study identified the factors affecting public acceptance of integrating the ChatGPT-type model with government services. It analyzed the relationship between the factors to provide a reference for decision-makers. This study introduced TAISM to form the LDA-grey-DEMATEL-TAISM method to provide an analytical paradigm for studying similar influencing factors.

An Adaptive Neuro-Fuzzy System With Integrated Feature Selection and Rule Extraction for High-Dimensional Classification Problems

A major limitation of fuzzy or neuro-fuzzy systems is their failure to deal with high-dimensional datasets. This happens primarily due to the use of T-norm, particularly, product or minimum (or a softer version of it). Thus, there are hardly any work dealing with datasets having features more than hundred or so. Here, we propose a neuro-fuzzy framework that can handle datasets with even more than 7000 features! In this context, we propose an adaptive softmin (Ada-softmin) which effectively overcomes the drawbacks of “numeric underflow” and “fake minimum” that arise for existing fuzzy systems while dealing with high-dimensional problems. We call it an Adaptive Takagi-Sugeno-Kang (AdaTSK) fuzzy system. We then equip the AdaTSK system to perform feature selection and rule extraction in an integrated manner. In this context, a novel gate function is introduced and embedded only in the consequent parts, which can determine the useful features and rules, in two successive phases of learning. Unlike conventional fuzzy rule bases, we design an enhanced fuzzy rule base (En-FRB), which maintains adequate rules but does not grow the number of rules exponentially with features that typically happens for fuzzy neural networks. The integrated Feature Selection and Rule Extraction AdaTSK (FSRE-AdaTSK) system consists of three sequential phases: (i) feature selection, (ii) rule extraction, and (iii) fine tuning. The effectiveness of the FSRE-AdaTSK is demonstrated on 19 datasets of which five are in more than 2000 dimension including two with more than 7000 features. This may be the first attempt to develop fuzzy rule based classifiers that can directly deal with more than 7000 features without requiring separate selection of features or any other dimensionality reduction method.

Using Subgroup Discovery to Relate Odor Pleasantness and Intensity to Peripheral Nervous System Reactions

Activation of the autonomic nervous system is a primary characteristic of human hedonic responses to sensory stimuli. For smells, general tendencies of physiological reactions have been described using classical statistics. However, these physiological variations are generally not quantified precisely; each psychophysiological parameter has very often been studied separately and individual variability was not systematically considered. The current study presents an innovative approach based on data mining, whose goal is to extract knowledge from a dataset. This approach uses a subgroup discovery algorithm which allows extraction of rules that apply to as many olfactory stimuli and individuals as possible. These rules are described by intervals on a set of physiological attributes. Results allowed both quantifying how each physiological parameter relates to odor pleasantness and perceived intensity but also describing the participation of each individual to these rules. This approach can be applied to other fields of affective sciences characterized by complex and heterogeneous datasets.

ROUGH SETS-BASED DECISION SUPPORT SYSTEMS FOR CUSTOMER RELATIONSHIP MANAGEMENT

Customer Relationship Management (CRM) plays a crucial role in maintaining and enhancing customer satisfaction and loyalty. To effectively manage customer relationships, organizations require decision support systems that can provide valuable insights and assist in making informed decisions. In this context, Rough Sets-Based Decision Support Systems (RS-DSS) have emerged as a promising approach. RS-DSS utilizes the principles of rough set theory to handle uncertainty and vagueness in customer data, enabling the discovery of hidden patterns and knowledge for effective CRM. This paper provides an overview of the application of RS-DSS in CRM, highlighting its benefits and challenges. The study also discusses various components of RS-DSS, including attribute reduction, rule extraction, and decision-making. Furthermore, the paper presents a case study to illustrate the practical implementation and potential outcomes of RS-DSS in CRM. Overall, RS-DSS holds significant potential in enhancing customer relationship management by leveraging rough set theory for decision support and improving organizational performance.

Double groups of gates based Takagi-Sugeno-Kang (DG-TSK) fuzzy system for simultaneous feature selection and rule extraction

Embedded feature selection methods based on fuzzy model have been well studied, in which the gate functions are usually used to distinguish the essential features. Fuzzy rules play a critical role in constructing fuzzy systems. However, few works simultaneously evaluate the quality of fuzzy rules during the fuzzy system based feature selection approaches. This article proposes double groups of gates based Takagi-Sugeno-Kang (DG-TSK) fuzzy model to simultaneously conduct feature selection and rule extraction in one training phase. Firstly, a novel gate function is introduced, which is embedded into the system. We call this function as M-gate since it is shaped like an M. Secondly, a new type of fuzzy rule base (FRB) is designed by transforming each data point into one fuzzy rule, which is named point-based FRB (P-FRB). Based on the M-gate and P-FRB, DG-TSK model is developed, in which M-gates are embedded in the antecedents for feature selection and consequents for rule extraction. Note that these two procedures are performed at the same time. We test DG-TSK on 18 classification datasets and compare it with other similar methods. The experiment results demonstrate that DG-TSK is effective.

EnviRule: an end-to-end system for automatic extraction of reaction patterns from environmental contaminant biotransformation pathways.

Transformation products (TPs) of man-made chemicals, formed through microbially mediated transformation in the environment, can have serious adverse environmental effects, yet the analytical identification of TPs is challenging. Rule-based prediction tools are successful in predicting TPs, especially in environmental chemistry applications that typically have to rely on small datasets, by imparting the existing knowledge on enzyme-mediated biotransformation reactions. However, the rules extracted from biotransformation reaction databases usually face the issue of being over/under-generalized and are not flexible to be updated with new reactions. We developed an automatic rule extraction tool called enviRule. It clusters biotransformation reactions into different groups based on the similarities of reaction fingerprints, and then automatically extracts and generalizes rules for each reaction group in SMARTS format. It optimizes the genericity of automatic rules against the downstream TP prediction task. Models trained with automatic rules outperformed the models trained with manually curated rules by 30% in the area under curve (AUC) scores. Moreover, automatic rules can be easily updated with new reactions, highlighting enviRule's strengths for both automatic extraction of optimized reactions rules and automated updating thereof. enviRule code is freely available at https://github.com/zhangky12/enviRule.

Diagnosing major depressive disorder and substance use disorder using the electronic health record: A preliminary validation study

BackgroundOne mechanism to examine if major depressive disorder (MDD) is related to the development of substance use disorder (SUD) is by leveraging naturalistic data available in the electronic health record (EHR). Rules for data extraction and variable construction linked to psychometrics validating their use are needed to extract data accurately. ObjectiveWe propose and validate a methodologic framework for using EHR variables to identify patients with MDD and non-nicotine SUD. MethodsProxy diagnoses and index dates of MDD and/or SUD were established using billing codes, problem lists, patient-reported outcome measures, and prescriptions. Manual chart reviews were conducted for the 1-year period surrounding each index date to determine (1) if proxy diagnoses were supported by chart notes and (2) if the index dates accurately captured disorder onset. ResultsThe results demonstrated 100% positive predictive value for proxy diagnoses of MDD. The proxy diagnoses for SUD exhibited strong agreement (Cohen's kappa of 0.84) compared to manual chart review and 92% sensitivity, specificity, positive predictive value, and negative predictive value. Sixteen percent of patients showed inaccurate SUD index dates generated by EHR extraction with discrepancies of over 6 months compared to SUD onset identified through chart review. ConclusionsOur methodology was very effective in identifying patients with MDD with or without SUD and moderately effective in identifying SUD onset date. These findings support the use of EHR data to make proxy diagnoses of MDD with or without SUD.

EARR: Using rules to enhance the embedding of knowledge graph

Knowledge graphs have been receiving increasing attention from researchers. However, most of these graphs are incomplete, leading to the rise of knowledge graph completion as a prominent task. The goal of knowledge graph completion is to find missing relations in a knowledge graph. Knowledge graph embedding represents the entities and relations in a low-dimensional embedding space, simplifying operations and allowing for integration with knowledge graph completion tasks. Several popular embedding models, such as TransE, TransH, TransR, TuckER, RotatE, and others have achieved impressive results on knowledge graph completion tasks. However, most of these methods do not incorporate background knowledge that could enhance the quality of knowledge embedding. Logic rules are adaptable and scalable, which can enrich background knowledge, and separating the attributes of entities can improve the relevance of relations and facilitate the accuracy of logic rule extraction. Thus, we propose a novel method, named Entity–Attribute–Relation–Rule (EARR), which separates attributes from entities and uses logic rules to extend the dataset, improving the accuracy of knowledge graph completion tasks. We define a total of six rules in this paper, including Rule 1–3, Rule 5, and Rule 6 for entities, and Rule 4 for entities and attributes. We evaluate our method based on the task of link prediction through two kinds of experiments. In the basic experiment, we compare our method with three benchmark models, namely, TransE, TransH, and TransR. In the experiment with different size datasets, FB24K and CoDEx, we evaluate our method on different size datasets with different models, including TransE, TuckER, and RotatE. The experimental results indicate that EARR can improve the quality of knowledge graph embedding.

Variable Clustered Fuzzy Rules for Self-Tuning Scheme for Respiratory Distresses by Similarity and the Phase Plane Trajectory Concept

This work proposes a fuzzy rule extraction methodology for a self-tuning fuzzy controller based on the fuzzy clustering method (FCM) and the similarity approach technique. The similarity technique and phase plane trajectory method are used to even lower the acquired rules. To show a potential rule extraction scheme, the self-tuning fuzzy-logic-based proportional-derivative (STFLPDC) with 49 expert fuzzy rules and 49 clustered fuzzy gain rules is used. The utility of the approach is validated using common clustering validity indices. With 49 initial clustered fuzzy rules, the suggested method addressed oxygen supply in a human respiratory model. After further reduction using the similarity strategy, 29 and 14 fuzzy rules remained. Parallel to this, a real-time benchmark application using 49, 21, and 16 extracted fuzzy gain rules is used to access the performance of a lab-based overhead crane. Finally, to investigate control performance in both models, the phase plane trajectory concept is used to generate as few as 13 fuzzy gain rules.