Fuzzy Reasoning Research Articles

Fuzzy Neural Logic Reasoning for Robust Classification

The efficacy of neural networks is widely recognized across a multitude of machine learning tasks, yet their black-box nature impedes the understanding of their decision-making processes. Such lack of explainability limits their use in high-stake fields such as medicine and finance, where transparent decision-making is essential. In contrast, traditional rule-based models offer clear input-output mappings, but often lag in performance when compared to their neural network counterparts. To address this challenge, this study introduces Fuzzy Neural Logic Reasoning (FNLR), a novel architecture that combines the best of both rule-based and deep learning models to achieve performance, interpretability, and noise robustness simultaneously. At its core, FNLR employs a “Symbolic Pre-training + Neural Fine-tuning” paradigm. Initially, the model adapts a pre-fitted binary decision tree. It then performs a “neuralization” process, replacing each node of the tree with a corresponding neural network equivalent. This transformation is facilitated through three shallow MLP modules, which are trained to emulate the relational operators intrinsic to decision trees. The model architecture is also extensible, allowing it to further boost expressiveness. Furthermore, FNLR incorporates fuzzy logic by proposing novel fuzzy relational operators, accounting for satisfaction degrees of propositions and thus eliminating rigid decision boundaries. This approach enhances model flexibility, enabling all paths of the decision tree to contribute to the target prediction in a weighted manner. Empirical evaluations on tabular datasets from various domains demonstrate that FNLR performs comparably to, or better than, state-of-the-art deep learning models designed for tabular data, while also exhibiting strong robustness to noise.

A Fuzzy Fusion Method for Multi-Ship Collision Avoidance Decision-Making with Merchant and Fishing Vessels

In multi-vessel collision avoidance decision-making, the collision between merchant and fishing vessels is a significant challenge. This paper proposes a fuzzy fusion method for making avoidance decisions under the influence of the navigation environment. First, C-means clustering was used to collect and analyze Automatic Identification System (AIS) data from fishing vessels. On this basis, the environment collision risk was determined using fuzzy reasoning. Second, the basic collision risk is obtained by calculating the DCPA and TCPA, and the integrated Collision Risk Index (CRI) is concluded by fuzzy logic through basic collision risk and the environment collision risk. The similar cases are extracted from the fuzzy case database, and collision avoidance decisions for merchant vessels are formulated following fuzzy adjustments. Finally, to validate the method, data from Chengshantou coastal waters is employed for verification. The results show that it can provide theoretical guidance and practical value for merchant vessels in making collision avoidance decisions.

A fuzzy evidential reasoning-based approach for assessing the navigation obstruction risk of shipwrecks in the Yangtze river

ABSTRACT This paper aims to evaluate the navigation obstruction risk represented by shipwrecks in shallow waters based on a fuzzy evidential reasoning approach. The purpose of this approach is to establish a hierarchical decision-making framework that considers ship conditions, traffic environment, distance from sensitive areas, and natural environment; to derive the belief rule base using the IF-THEN rule with a belief structure; and to obtain the crisp values of navigation obstruction risk of shipwrecks via evidential reasoning. This approach is applied to the navigation obstruction risk assessment of 10 historical shipwrecks in the Yangtze River, and the evaluation results are consistent with historical data. Consequently, this approach can be used for assisting in shipwreck salvage decision-making in navigable waters.

Intelligent Positioning Algorithm for Urban Substation Personnel based on Wireless Sensor Networks

In order to solve the problem of accurate and low-cost location of substation personnel in digital cities, a substation personnel location system based on wireless sensor cloud computing network is proposed. ZigBee wireless sensor cloud computing network is introduced into the substation to improve the direct location algorithm of substation personnel, and a fuzzy reasoning algorithm is proposed. The algorithm takes the signal strength received by each reference node and the relative distance between the reference nodes as input. After fuzzy, fuzzy reasoning and deblurring, the reliability of the received signal strength of each reference node is obtained, and then three reference nodes with high reliability are selected for trilateral positioning calculation. The experimental results show that the positioning error after improvement is more stable than that before improvement, and the maximum error before improvement is 1.4115m. Practice has proved that the algorithm can significantly improve the positioning accuracy of substation personnel without adding any hardware and using fewer nodes.

Dementia Classification Approach Based on Non-Singleton General Type-2 Fuzzy Reasoning

Dementia is the most critical neurodegenerative disease that gradually destroys memory and other cognitive functions. Therefore, early detection is essential, and to build an effective detection model, it is required to understand its type, symptoms, stages and causes, and diagnosis methodologies. This paper presents a novel approach to classify dementia based on a data set with some relevant patient features. The classification methodology employs non-singleton general type-2 fuzzy sets, non-singleton interval type-2 fuzzy sets, and non-singleton type 1 fuzzy sets. These advanced fuzzy sets are compared with traditional singleton fuzzy sets to evaluate their performance. The Takagi–Sugeno–Kang TSK inference method is used to handle fuzzy reasoning. In the process, the parameters of the membership functions (MFs) and rules are obtained using ANFIS, and non-singleton MFs are optimized with PSO. The results demonstrate that non-singleton general type-2 fuzzy sets improve classification accuracy compared to singleton fuzzy sets, demonstrating their ability to model the uncertainties inherent in the diagnosis of dementia. This improvement suggests that non-singleton fuzzy systems offer a more robust framework for developing effective diagnostic tools in the medical domain. Accurate classification of dementia is of utmost importance to improve patient care and advance medical research.

Application of Fuzzy Reasoning with Fusion Rules in Intelligent Information Processing

The core of artificial intelligence (AI) research is intelligent information processing, and fuzzy reasoning and fuzzy neural networks are significant research areas in models of intelligent information processing. The study examines the robustness of fuzzy reasoning by using the property characteristics of triangular modal operators and implication operators, which are used to analyse the Lipschitz property of fuzzy operators and its corresponding property characteristics of triangular modal operators and implication operators. Inference operators are used to investigate the robustness and error-control capabilities of fuzzy operators for fuzzy reasoning. The results showed that the robustness of quasi-copula fuzzy reasoning with fusion rules is better, and the corresponding maximum output perturbation is lowest at 0.36 when the fuzzy operator is T[Formula: see text]&R[Formula: see text] and the corresponding maximum output error is lowest at 0.41 when the fuzzy operators are T[Formula: see text]&R[Formula: see text] and T[Formula: see text]&R[Formula: see text]. This shows the optimal performance of the fuzzy associative memory model with fuzzy rule for quasi-copula fuzzy operators and can improve the theoretical technology. The best-performance fuzzy copula operator of the fuzzy associative memory model can enhance the theoretical foundation and technical support for the processing of intelligent information.

Application of the Sugeno integral in Fuzzy Rule-Based Classification

Fuzzy Rule-Based Classification System (FRBCS) is a well-known technique to deal with classification problems. Recent studies have considered the usage of the Choquet integral and its generalizations (e.g.: CT-integral, CF-Integral and CC-integral) to enhance the performance of such systems. Such fuzzy integrals were applied to the Fuzzy Reasoning Method (FRM) to aggregate the fired fuzzy rules when classifying new data. However, the Sugeno integral, another well-known aggregation operator, obtained good results in other applications, such as brain–computer interfaces. These facts led to the present study, in which we consider the Sugeno integral in classification problems. That is, the Sugeno integral is applied in the FRM of a widely used FRBCS, and its performance is analyzed over 33 different datasets from the literature, also considering different fuzzy measures. To show the efficiency of this new approach, the results obtained are also compared with previous studies that involved the application of different aggregation functions. Finally, we perform a statistical analysis of the application.

Temperature control technology for PCR

AbstractIn order to solve the obvious nonlinear problem of temperature and complex structure of PCR instrument during nucleic acid amplification. In this paper, a new nucleic acid amplification device and temperature control algorithm were proposed. In the device, in order to improve the rise and fall rate and make the whole reaction device smaller and simpler, this paper uses a microfluidic chip for nucleic acid reaction. At the same time, in the warming and cooling module, the temperature is controlled by the semiconductor chilling plate, the air‐cooled cooling device and the heat sink structure, which greatly improves the speed of nucleic acid amplification. In the algorithm, a hybrid algorithm is designed, using Particle Swarm Optimization (PSO) to optimize PID algorithm parameters, and then based on fuzzy theory, according to the temperature control requirements of nucleic acid amplification, fuzzy rules are analyzed and fuzzy reasoning is carried out, and then combined with PID to achieve rapid response and overshooting control of temperature control. Finally, the measurement noise is filtered by Kalman filter. Finally, COMSOL and MATLAB software are used to simulate and compare, and it is proved that the device has a certain heat dissipation effect in the process of nucleic acid amplification. This algorithm can improve the accuracy and robustness of the control system, improve the response speed, reduce the overshoot, shorten the adjustment time, and restrain the interference.

Bio-inspired EEG signal computing using machine learning and fuzzy theory for decision making in future-oriented brain-controlled vehicles

One kind of autonomous vehicle that can take instructions from the driver by reading their electroencephalogram (EEG) signals using a Brain-Computer Interface (BCI) is called a Brain-Controlled Vehicle (BCV). The operation of such a vehicle is greatly affected by how well the BCI works. At present, there are limitations on the accuracy of BCI recognition, the number of distinguishable command categories, and the execution duration of command recognition. Consequently, vehicles that are exclusively controlled by EEG signals demonstrate suboptimal control performance. To address the difficulty of improving the control capabilities of brain-controlled cars while maintaining BCI performance, a fuzzy logic-based technique called as Fuzzy Brain-Control Fusion Control is introduced. This approach uses Fuzzy Discrete Event System (FDES) supervisory theory to verify the accuracy of the driver's brain-controlled directives. Concurrently, a fuzzy logic-based automatic controller is developed to generate decisions automatically in accordance with the present state of the vehicle via fuzzy reasoning. The final decision is then reached through the application of secondary fuzzy reasoning to the accuracy of the driver's instructions and the automated decisions to make adjustments that are more consistent with human intent. A clever BCI gadget known as the Consistent State Visual Evoked Potential (SSVEP) is utilized to show the viability of the proposed technique. We recommend that additional research should be conducted at this time to confirm that our recommended system may further improve the control execution of BCI-fueled cars, regardless of whether BCIs have special limitations.

Development of modified fuzzy FMEA method in environmental risk assessment of earth dams

The investigations have shown that the construction of the dam and its related facilities have significant physical–chemical and ecological effects on the ecosystem. Failure Mode and Effects Analysis (FMEA) is a technique for ranking risks in projects to construct dams, but it has many deficiencies and ambiguities. Therefore, to prevent the shortcomings of the classical method, the modified fuzzy inference system (MFIS-FMEA) method has been used by creating a two-stage model to more accurately assess the risk of Eyvashan Dam. First, all the considered indicators are weighted using the Shannon entropy method, and the environmental risk is prioritized using the Fuzzy OWA method. In this study, two-stage fuzzy reasoning and a Max–Min combination rule are used. When severity (SEV) and occurrence (OCC) variables are combined, the critical risk index (RCI) values are predicted in the first stage. RCI and detection index (DET) input are then used to predict the MFIS-RPN in the second stage. The results of the risk priority number (RPN) in the MFIS-RPN method are much more accurate and serious than the FIS-RPN method due to the two-stage nature and the use of new language terms. The results of the proposed MFIS-RPN technique show that the highest RPN was obtained with immediate action in the dam construction phase for soil erosion and soil pollution and in the dam operation phase for aquatic and water pollution. Therefore, due to the increase in risk score, it is necessary to take immediate and more accurate monitoring during the construction and operation phases.

Predicting daily wind speed using coupled multi-layer perceptron model with water strider optimization algorithm based on fuzzy reasoning and Gamma test

Predicting daily wind speed using coupled multi-layer perceptron model with water strider optimization algorithm based on fuzzy reasoning and Gamma test

A fault diagnosis method of hot spots for photovoltaic clusters based on model parameters

AbstractUtilizing the direct current‐side electrical data resources of the photovoltaic power generation system on the FusionSolar platform, this study investigates the impact of hot spot faults on the output characteristics of photovoltaic strings and proposes a hot spot fault diagnosis method based on time series waveform characteristics. By analyzing the mechanisms of hot spot generation and evolution, as well as the characteristic differences in I–V curves and time series compared to other types of faults, the waveform variation patterns of hot spots in current and voltage time series are obtained. A function form suitable for hot spot fault waveform characteristics in time series graphs is constructed, and fault diagnosis feature vectors are extracted. Combining field operation and maintenance experience, a fuzzy reasoning fault diagnosis system is established to determine the causes and estimate the severity of hot spot faults. Experimental results indicate that hot spot faults have unique and corresponding variations in the current/voltage time series waveforms of the string output. The constructed function form can clearly represent the waveform variation patterns, and the established fuzzy reasoning system can achieve effective and reliable diagnosis of hot spot faults.

Light but fruitful: enhanced fuzzy inference via weight-guided selection of rules with attribute weights

Inference using fuzzy rules enables decision-making that is supported with imprecise knowledge. Unlike conventional fuzzy reasoning approaches which directly perform pattern-matching in response to an input observation, recent techniques have integrated rule-firing-based and rule interpolating-based inference methods. This is in order to address challenging issues where observations are of different matching degrees to the rules within a given rule base, including unmatched ones. While applied generally, such a unified inference mechanism may become too complex to exploit the entire rule base for deriving a reasonable conclusion. In practice, only a small number of ‘appropriate’ rules are selected to accomplish the required inference. This paper presents an enhanced integrated fuzzy inference mechanism, which is fed with fewer rules returned by a weight-guided selection procedure. In particular, the weights of rule attributes are utilised in a dual manner: guiding the selection of appropriate rules for rule firing and determining the nearest neighbouring rules for rule interpolation. The resulting mechanism is applied to a real-world problem, empirically demonstrating its significant efficacy.

A multi-method examination of barriers to traceability in Industry 5.0-enabled digital food supply chains

PurposeRecent worldwide developments have altered how businesses operate. As a result, when making business decisions, the emphasis for many industries has shifted towards digital adoption to ensure sustainability, and the food supply chain is no exception. However, a substantial gap exists in assessing the barriers to a digitised food supply chain enabled by Industry 5.0 technologies. This study strives to bridge the gap by identifying and assessing the barriers to improved traceability.Design/methodology/approachFor this study, a mixed method approach was used encompassing both qualitative and quantitative techniques, including an online survey, exploratory factor analysis (EFA), and the fuzzy evidential reasoning approach (FERA). The literature survey and expert opinion first yielded a list of 18 barriers, which were subsequently examined using EFA. As a result, four barriers were removed. The remaining 14 barriers were then assessed using FERA from the perspectives of the Technology, Organisation and Environment (TOE) framework. Further, a sensitivity analysis was performed to test the model’s reliability.FindingsThe present study resulted in the prioritisation of barriers from the TOE perspective. According to the findings, the top three barriers that impede the traceability of Industry 5.0-enabled digital food supply chains are Limited Digital and Physical Infrastructure, Inadequate Capital Investment, and the Intricate Supply Chain Framework.Research limitations/implicationsThe findings from this research will prove valuable for decision-makers, practitioners and policymakers in developing methods for improving traceability within the digital food supply chain. Concerned stakeholders may use the findings to identify and take immediate action for better decision-making.Originality/valueThis study’s originality lies in its position as one of the first to identify and examine the challenges to better traceability in an Industry 5.0-enabled digital food supply chain. It also adds value by broadening the TOE framework’s scope in the Industry 5.0-enabled digital food supply chain context.

Scikit-ANFIS: A Scikit-Learn Compatible Python Implementation for Adaptive Neuro-Fuzzy Inference System

The Adaptative neuro-fuzzy inference system (ANFIS) has shown great potential in processing practical data from control, prediction, and inference applications, reflecting advantages in both high performance and system interpretability as a result of the hybridization of neural networks and fuzzy systems. Matlab has been a prevalent platform that allows to utilize and deploy ANFIS conveniently. On the other hand, due to the recent popularity of machine learning and deep learning, which are predominantly Python-based, implementations of ANFIS in Python have attracted recent attention. Although there are a few Python-based ANFIS implementations, none of them are directly compatible with scikit-learn, one of the most frequently used libraries in machine learning. As such, this paper proposes Scikit-ANFIS, a novel scikit-learn compatible Python implementation for ANFIS by adopting a uniform format such as fit() and predict() functions to provide the same interface as scikit-learn. Our Scikit-ANFIS is designed in a user-friendly way to not only manually generate a general fuzzy system and train it with the ANFIS method but also to automatically create an ANFIS fuzzy system. We also provide four kinds of representative cases to show that Scikit-ANFIS represents a valuable addition to the scikit-learn compatible Python software that supports ANFIS fuzzy reasoning. Experimental results on four datasets show that our Scikit-ANFIS outperforms recent Python-based implementations while achieving parallel performance to ANFIS in Matlab, a standard implementation officially realized by Matlab, which indicates the performance advantages and application convenience of our software.

Prediction of the creeping of AFC based on fuzzy reasoning and Bi-LSTM fusion iteration

The creeping of Armoured Face Conveyor (AFC) is an engineering problem that needs to be avoided in coal mining production process. In this paper, a method for predicting the creeping accident of AFC based on fuzzy reasoning and Bi-directional Long Short-Term Memory (Bi-LSTM) fusion iteration is put forward. Firstly, through the force analysis of the AFC and the fuzzy correlation analysis method in the actual operation process, the reasons for the creeping of AFC are analyzed; Secondly, according to the propulsion characteristics of the AFC in the time sequence development, the method of the AFC running track based on Bi-LSTM neural network is proposed; Then, on the basis of the virtual transformation of the prediction results, a judgment mechanism for the extent of the creeping of the AFC based on fuzzy evidence reasoning based on fuzzy comprehensive evaluation method and Dempster-Shafer evidence theory (D-S evidence theory) is established; Finally, the analysis on the creeping of 9711 full-mechanized mining face in Kaiyuan Mine under virtual environment after 6 cycles of continuous advancement shows that the extent of creeping of AFC is relatively high and coal mining accidents are likely to occur.

FDKT: Towards an Interpretable Deep Knowledge Tracing via Fuzzy Reasoning

In educational data mining, knowledge tracing (KT) aims to model learning performance based on student knowledge mastery. Deep-learning-based KT models perform remarkably better than traditional KT and have attracted considerable attention. However, most of them lack interpretability, making it challenging to explain why the model performed well in the prediction. In this paper, we propose an interpretable deep KT model, referred to as fuzzy deep knowledge tracing (FDKT) via fuzzy reasoning. Specifically, we formalize continuous scores into several fuzzy scores using the fuzzification module. Then, we input the fuzzy scores into the fuzzy reasoning module (FRM). FRM is designed to deduce the current cognitive ability, based on which the future performance was predicted. FDKT greatly enhanced the intrinsic interpretability of deep-learning-based KT through the interpretation of the deduction of student cognition. Furthermore, it broadened the application of KT to continuous scores. Improved performance with regard to both the advantages of FDKT was demonstrated through comparisons with the state-of-the-art models.

Research on fire detection method of complex space based on multi-sensor data fusion

Efficient and reliable fire detection methods are essential for addressing complex spatial characteristics of older residential communities, which often face poor fire safety conditions, various fire types, and challenges in rescue operations. In response to the problem of lacking comprehensive analysis of multidimensional data in traditional fire detection, which often leads to false alarms and missed alarms, this paper proposes a fire detection method based on multi-sensor data fusion. Various sensors are employed, including smoke sensors, temperature sensors, CO sensors, and flame sensors. These sensors collect multidimensional data, which are fused using improved adaptive filters and fuzzy Bayesian logical reasoning algorithms to establish a fire detection model based on multi-sensor data fusion. To additionally, false alarms and missed detections caused by sensor damage are further solved by exploring hidden spaces. Experimental results demonstrate that the proposed fire detection system based on multi-sensor data fusion effectively analyses fire occurrence and progression in older residential communities, and performs stability, accuracy and real-time property.

Rainfall Assessment Using Weighted Interval Type-2 Fuzzy Inference System

This study proposes an integrated model for assessing rainfall in Chennai using the Interval type-2 fuzzy reasoning technique and the Analytic Hierarchy Process (AHP). Interval Type-2 Fuzzy Inference System (IT2FIS) is employed to describe complex relationship between the rainfall variables and rainfall rate by considering individual weights of those variables through the aggregation of criteria weights using AHP. The suggested approach has an edge over its predecessors in terms of modeling the inter-personal and intra-personal uncertainty involved in rainfall rate classification. Finally, the developed rainfall model (RM) is applied on the historical dataset collected from Indian Meteorological Department (IMD). The actual data and the IT2FIS model’s performance are compared. Correlation coefficient ([Formula: see text]) and Bland–Altman Plot (BAP) have been used to evaluate the performance metrics of the proposed model. The outcome suggests that the AHP-IT2FIS model can accurately estimate rainfall over time, indicating its potential for long-term use.

Analysis and multi-objective optimization design of sinusoidal DSEM with two different excitation modes based on Gray-Fuzzy-Taguchi method

The nonlinearity of sinusoidal doubly salient electro-magnetic machine (SDSEM) leads to the fuzzy optimization range of its design parameters. And there is a conflict problem in multiple optimization objectives. Therefore, the multi-objective optimization of SDSEM with two different excitation modes is carried out based on the Gray-Fuzzy-Taguchi method. Firstly, the proposed sinusoidal method of square wave back electromotive force (EMF) phase modulation is introduced. And the key parameters to improve the symmetry and sinusoidal degree of the back EMF waveform are pointed out. Then, the sensitivity of key parameters is analyzed and the signal-to-noise (S/N) ratio is calculated by Taguchi orthogonal test. Secondly, the S/N ratio is linearly normalized by grey correlation analysis. Then, fuzzy reasoning is used to synthesize multiple performance indexes of the motor into a multiple performance characteristics index (MPCI) value, and the optimal scheme is obtained. Finally, the optimized SDSEM with concentrated magneto-motive forces (SDSEM-CF) and SDSEM with distributed magneto-motive forces (SDSEM-DF) are simulated and compared. The SDSEM-DF prototype is developed and verified by experiments. The results show that the no-load back EMF of the prototype has a good sinusoidal degree. Based on vector control, the sinusoidal drive of DSEM is realized without increasing the control complexity, which greatly reduces the torque ripple of the flux reluctance motor.