Clustering is a basic data mining operation that groups data points with similar inherent structure. Among clustering techniques, Density Peak Clustering (DPC) is notable for detecting clusters of arbitrary shapes without requiring the number of clusters in advance. However, DPC suffers from parameter-sensitive local density estimation, inadequate handling of noise and boundary points, and rigid binary cluster assignments. To overcome these limitations, fuzzy logic is often embedded in DPC, but the selection of the most appropriate membership function is still an open research question. In this paper, we propose an enhanced DPC variant with three methodological improvements: (i) substituting cutoff distance-based density estimation with a K-Nearest Neighbors (KNN) functioned kernel to achieve stable and robust density estimation, (ii) adding a noise parameter Lambda ( λ ) to better identify and distinguish noise and boundary points, and (iii) using fuzzy membership functions to allow for probabilistic and soft cluster assignments of data points. Comparative analyses of four fuzzy membership functions (i.e., Gaussian, Combination Gaussian, Trapezoidal, and Triangular) were performed on real, synthetic, and high-dimensional datasets. The experimental results indicate that the proposed algorithm with the Gaussian fuzzy membership function outperforms other membership functions and traditional clustering algorithms including the original DPC, FKNN, and DPC-DBFN in terms of clustering accuracy, stability, adaptability, and noise resistance, and is therefore part of our final suggested method. The proposed method overall relieves original DPC shortcomings by strengthening adaptability, accuracy, and applicability to complex real-world clustering tasks. • Substituting standard cutoff-distance-based kernel with KNN for enhanced clustering. • Introducing λ parameter to manage noise and boundary points for separating clusters. • Introducing fuzzy neighborhood kernel for soft cluster membership assignment. • Investigating the impact of several fuzzy membership functions on clustering. • Proposed strategy outperforms original DPC, FKNN, and DPC-DBFN on datasets.

A hybrid admittance control strategy for fluid-driven origami actuators in lower limb exoskeleton

The law of contraposition is one of the most well-known tautologies in classical logic. In addition, there are two other notions of contrapositions: the law of right contraposition and the law of left contraposition. In fuzzy logic, these tautologies are modeled by a fuzzy implication and a fuzzy negation. The characterization of fuzzy implications satisfying the laws of right or left contraposition with respect to an arbitrary fuzzy negation is a problem that has gained attention recently. This article aims to propose characterizations of such implications, presenting necessary and sufficient conditions under which a fuzzy implication satisfies these laws with respect to an arbitrary fuzzy negation.

An approach based on geophysical vertical electrical sounding resistivity (VESR) and fuzzy logic modeling to explore a multi-layered system geometry and groundwater prospectivity. Case of the north-eastern Tadla plain, Morocco

Automated detection system based on type-3 fuzzy logic for evaluating fly infestation level in cattle

Ordering the chaos of sustainable supply chains: A q-rung fuzzy hypersoft framework for multi-attribute green supplier selection

Closure operators and systems play a significant role in a variety of areas of fuzzy logic. While the condition of monotony for ordinary closure operators has a straightforward form, two basic conditions of monotony naturally arise from the existing examples in a fuzzy setting. To unify these two conditions, two approaches can be found in the literature, one based on the notion of a filter of truth degrees and the other on the notion of a linguistic hedge. We present results connecting these approaches, explore their variants, and provide a notion of monotony that subsumes both the filter-based and hedge-based approaches. We study properties of this general concept of monotony and discuss open problems along with topics for future research.

Morphology-informed deep learning for risk assessment of filamentous bulking in a full-scale industrial wastewater treatment plant.

Although there has been significant progress in technology, the human factor remains a key contributor to marine accidents. To shed light on the academic perspective regarding the marine accident-human factor pairing, this study aims to clarify and present intellectual structure via bibliometric analysis. Furthermore, a detailed investigation was implemented using the studies from the last 5 years to better understand emerging trends for the human factor in marine accidents. The results reveal that China and Türkiye are the most productive countries in this field and that institutions and authors from these countries are at the forefront. Especially in recent years, it has been observed that the ‘autonomous ship’ phenomenon has attracted great attention and has become one of the trending topics. In addition to bibliometric analysis, methodological trends were identified by analyzing relevant studies from the last five years. The findings indicate that statistical methods, Bayesian networks, fuzzy logic, SLIM, and HFACS are the most commonly employed methodologies. It is also found that there is a significant trend towards adopting hybrid approaches that integrate different methods to provide more comprehensive and reliable assessments. By combining bibliometric and systematic content analyses, this study clarifies the intellectual structure of the field and highlights current methodological trends. ------------------------------------------------------------------------------Cite this article: APA Style:Cinar, F., Kaya, C., Akyuz, E., & Demirel, H. (2026). Human factor in maritime accidents and related analyzing methods: A bibliometric review. Maritime Technology and Research, 8(4), 285640. https://doi.org/10.33175/mtr.2026.285640 MDPI Style:Cinar, F.; Kaya, C.; Akyuz, E.; Demirel, H. Human factor in maritime accidents and related analyzing methods: A bibliometric review. Marit. Technol. Res. 2026, 8, 285640. https://doi.org/10.33175/mtr.2026.285640 Vancouver Style:Cinar F, Kaya C, Akyuz E, Demirel H. (2026). Human factor in maritime accidents and related analyzing methods: A bibliometric review. Marit. Technol. Res. 8(4):285640. https://doi.org/10.33175/mtr.2026.285640 ------------------------------------------------------------------------------ Highlights A bibliometric analysis is conducted for the role of human factor in maritime accidents. A detailed evaluation of studies of the last 5 years is performed. China and Türkiye are the most productive countries in the field. Bayesian Networks are determined to be the most widely used methodology in the papers. The ‘autonomous ship’ phenomenon has attracted great attention in recent years.

In today’s rapidly evolving IT infrastructure and the ever-increasing number of cyber threats, security information and event management (SIEM) systems generate a huge volume of routine alerts. However, a single isolated event is rarely sufficient to reliably conclude that a cyber incident has occurred, as complex targeted attacks typically manifest themselves through a set of multidimensional and interconnected events that form a time-structured process. Traditional approaches to threat detection in monitoring systems are primarily based on rigid correlation rules or static thresholds. Such methods have significant limitations, do not take into account the multifaceted nature of security events, poorly model the uncertainty inherent in the data, and create a too sharp binary transition between the normal state and the incident itself, which inevitably leads to a significant number of false positives. The article is devoted to the development of a model for detecting cyber incidents in SIEM event logs, which is based on a fuzzy hypergraph representation of security events. An approach is proposed in which each individual event is considered and formalized as a hyperedge that flexibly connects a set of heterogeneous system entities, such as a target host, a compromised user, an external IP address, a system process, or an applied attack technique. For a comprehensive assessment of the threat level, a fuzzy function of the local incidence of the event and a mathematical mechanism for aggregating the parameters of the connected component of the hypergraph are used. This measure is calculated taking into account key criteria: the degree of anomaly of deviation from the typical behavior profile, the a priori criticality of the triggered rule, contextual consistency within a given time window, semantic significance, and accumulated historical suspicion of the involved entities. Formalization of contextual dependence through the definition of non-trivial intersection of entities in the vicinity of the event allows for the effective interpretation of any cyber incident as a detected connected fuzzy substructure in the general hypergraph of SIEM events. The advantages of the proposed model lie in the possibility of deep integration of multi-entity relationships with the fuzzy logic apparatus, which provides the formation of a graded risk assessment, significantly increases the accuracy of identification of complex multi-stage attacks and optimizes analytics processes.

This article addresses the formation control of under-actuated multiple autonomous surface vehicles (MASVs) with input quantization under communication delay conditions, which is influenced by external marine disturbances and internal model uncertainties. A two-level distributed guidance and quantization control architecture based on the Nussbaum function is proposed. At the communication level, a time-delay distributed event-triggered extended state observer (ESO) is introduced to estimate the state of the single virtual leader, thereby further conserving communication resources. At the control level, the distributed formation guidance laws based on ESO are proposed in the kinematic subsystem, enabling effective tracking of the ideal trajectory while estimating the states of neighboring agents and unknown ocean disturbances. In the dynamics subsystem, a fuzzy logic system is used to estimate the uncertain terms within the model, and a linear model is introduced to handle the input quantization process. Additionally, the fuzzy adaptive quantization tracking control laws based on the Nussbaum function are proposed to achieve accurate tracking of the guidance signals and reduce actuator execution frequency, which makes the proposed scheme more applicable to practical marine engineering scenarios. The stability of the designed control structure is proven based on stability theory, and all signals within the closed-loop control system are uniformly ultimately bounded. Simulation experiments validate the rationality and effectiveness of the proposed method.

Predefined-time affine formation tracking control of unmanned surface vehicles with input saturation via adaptive fuzzy observers.

Urban pipeline infrastructure plays a vital role in ensuring the operational efficiency and service reliability of modern utility systems, especially in industrial regions. While previous studies have focused primarily on pipe failure prediction, limited research has addressed the forecasting of key pipeline performance indicators such as velocity, pressure, and head loss within the context of infrastructure asset management. This study investigates the performance of advanced machine learning (ML) models, PSO-ANN, Genetic CNN, Quantum SVR, Fuzzy Logic Tree, and Bayesian GPR, in predicting three critical output variables: velocity, head loss, and pressure. A dataset comprising 91 instances with geometric and hydraulic descriptors was employed, and descriptive statistics revealed significant variability in flow-dependent parameters. SHAP-based sensitivity analysis highlighted elevation (0.9287) as the dominant factor for pressure prediction, while flow rate (0.4574) and diameter (0.2273) strongly influenced head loss. For velocity, flow rate (0.1139) emerged as the most influential, though other parameters also contributed, justifying their inclusion in the modeling framework. The models were trained using data from the Gadhra Water Distribution Network (District Metered Area-03) in East Singhbhum, Jamshedpur, India. Model evaluation was conducted using R², RMSE, MAE, and MAPE. Results demonstrated a clear performance hierarchy, with Bayesian GPR and Fuzzy Logic Tree exhibiting superior accuracy and stability (R² ≥ 0.98, RMSE ≤ 0.06, MAPE ≤ 0.13), whereas PSO-ANN and Genetic CNN showed relatively weaker performance. The near-perfect R² observed for Fuzzy Logic Tree reflects the small dataset size and its high capacity, highlighting that generalization may be limited in larger or unseen datasets. The analysis of regressor plots, residual distributions, and normalized accuracy matrices further validated these findings. Overall, the study establishes Bayesian GPR and Fuzzy Logic Tree as robust predictive tools for hydraulic modeling while acknowledging dataset constraints that may affect generalization.

Retraction: Evaluation of influencing factors of China university teaching quality based on fuzzy logic and deep learning technology

The field of medical research has advanced remarkably in the twenty-first century; however, the healthcare industry faces significant challenges, including rising costs, increasing demand, and constrained resources. These factors make effective management of healthcare systems crucial. Efficient systems are those that better use resources, deliver services, and reduce waiting times. The paper addresses the issue of healthcare staffing optimization by presenting a new model, the Fuzzy-Based Time-Dependent Multi-Server, Multi-Queueing (FB-TDMS-MQ) System. This model combines fuzzy logic with a genetic algorithm (GA) to optimize staffing levels based on real-time patient needs and service times, a capability that traditional fixed-staffing models cannot accommodate. To demonstrate the model's application in a real-world setting, a case study is conducted at Dhanwantri Hospital and Research Centre (DHRC) in Jaipur, a multi-specialty hospital. The model's performance is evaluated using simulation studies. The implementation of the FB-TDMS-MQ model led to significant improvements. Simulation studies demonstrated that the average "peak-hour waiting time" drastically reduced by 72.73% after incorporating fuzzy logic modifications. Additionally, the GA optimization approach resulted in a 50.2% reduction in average waiting time, showing superior performance compared to static staffing models. The model's sensitivity analysis proved highly useful in the case of unexpected events in the healthcare system. The FB-TDMS-MQ model proved to be adaptable and effective in real-time healthcare staffing optimization. It demonstrated a reduction in waiting times and the ability to handle unexpected events, showing that the model could optimize staffing dynamically in fast-changing healthcare environments. The real-time control and modifications provided by the model have significant potential for improving hospital management and staff allocation.

Alzheimer's is a neurological disease that leads to severe memory loss in patients. This article employs a novel systematic workflow, the Alzheimer Detection System (ADS), for Alzheimer and Non-Alzheimer brain MRI image classification process, which uses the proposed Deep Feature Incorporated Swin Transformer Model (DFISTM). This proposed DFISTM is designed with edge detection, pixel-transformation process, convolutional feature computation, and the Swin Transformer Model (STM) classifier. The edge pixels in the brain MRI images are detected through the Mamdani fuzzy logic, and they are fused using Mamdani fuzzy rules to enhance the pixel intensity. Then the curvelet transform is applied on the detected edge pixels in the image in order to obtain the decomposed curvelet coefficients, where the decomposition produced low- and high-frequency band components from the fused brain MRI. The proposed deep learning-based feature extraction module, Dynamic Feature Enhanced Convolutional Network (DFECN), is used to compute the deep convolutional features from the two-dimensional curvelet coefficient matrix. These features are then classified into either Alzheimer or non-Alzheimer brain MRI images using the proposed STM classification approach. The novelty of this research work is to construct a DFECN model to compute the fine-grained feature maps with a minimum number of internal convolutional layers. This research article uses two Alzheimer datasets, Mendeley and Kaggle to train, validate, and test the proposed system with respect to the parameters Alzheimer Detection Sensitivity (ADSe), Alzheimer Detection Specificity (ADSp), Alzheimer Detection Precision (ADP), and Jaccard Index (JI).

ABSTRACT Modern Edge Computing (EC) platforms are designed to manage a large amount of sensor data from different sensor networks deployed on the edge. However, the network parameters of the Sensor Networks (SNs) may not necessarily be aligned with the design. Principles of legacy networks. Most of the existing works are designed to address either the resource efficiency or the performance aspects alone. In this article, we propose a hybrid approach, namely, Particle Swarm Optimization‐based Fuzzy Reinforcement Learning (PSO‐FRL) method that leverages the optimization capabilities of the PSO method and the adaptability features of the Reinforcement Learning (RL) method along with the fairness features of Fuzzy Logic. The proposed hybrid method efficiently designs the task scheduling and resource allocation of Edge Computing‐based SNs, which is a complex optimization problem. Using the proposed hybrid method, the sensor networks resource efficiency is improved and the task scheduling is optimized that lead to the improvements in throughput, Quality of Service (QoS), spectral efficiency and network lifetime, by achieving an average task scheduling efficiency of 98% over the PSO alone and RL alone. Hence, the proposed design is a suitable trade‐off between short‐term performance gains and long‐term adaptability. It is also scalable and is expected to support the large number of next generation Internet‐of‐Things (IoT)‐enabled Sensor Networks for use cases in smart city, industrial automation, and environmental monitoring, and so forth.

Robotic exoskeletons hold significant potential for clinical rehabilitation as well as human performance augmentation. Nevertheless, identifying robust and adaptable control approaches to enable smooth human–machine interaction through dynamic environments with varying task requirements remains a primary technical challenge. This paper presents the design and implementation of interval type-2 fuzzy logic modified PID (PI-D) controller (IT2-FLPI-DC) for multi-joint lower limb exoskeleton (LLE). The purpose of LLE is to assist, augment or restore movement, and function in the human legs for those who suffers spinal cord injury, stroke, etc. For performance analysis, the proposed controller is compared with interval type-2 fuzzy logic PID controller (IT2-FLPIDC). Simulation results show that the proposed controller achieves faster settling time and less overshoot when compared to IT2-FLPID controller.

This paper proposes a hybrid fuzzy-reinforcement learning framework for real-time task scheduling and resource optimization in medical edge computing. The proposed framework introduces a direct mathematical coupling between fuzzy inference and reinforcement learning rather than a simple hybrid combination. By integrating fuzzy logic to evaluate task urgency, bandwidth congestion, and battery constraints with a reinforcement learning agent, the framework dynamically refines offloading strategies. Simulation results in Internet of Medical Things (IoMT) environments demonstrate the framework's superiority over existing benchmarks, achieving up to 42% lower average latency, 31% greater energy efficiency, and up to 20% improvement over Dynamic Priority-Based Task Scheduling and Adaptive Resource Allocation (DPTARA) under the evaluated benchmark settings in the completion rate of critical tasks. Operating with a linear time complexity of [Formula: see text] the proposed system guarantees scalable and robust performance for delay-sensitive healthcare applications. Experimental results across four benchmark IIoT healthcare datasets demonstrate the effectiveness of the proposed framework. Specifically, the model achieves average accuracy improvements of 2.8-4.6% over state-of-the-art baselines, while reducing false negative rates by up to 35.4%. In addition, the proposed fuzzy-reinforcement learning scheduler decreases average task latency by 23.7%, improves resource utilization by 18.9%, and enhances system adaptability under dynamic workload conditions. These results confirm the framework's robustness, scalability, and suitability for real-time medical edge computing environments.

The landscape of drug discovery is being rapidly transformed by the integration of computational intelligence (CI) techniques with big data resources in medicinal chemistry. Traditional drug development methods are often time-consuming, costly, and prone to high attrition rates. In contrast, data-driven and algorithmic approaches-powered by machine learning, deep learning, and hybrid models-enable rapid, precise, and predictive decision-making across all phases of drug design. This review provides a comprehensive overview of how CI techniques, including supervised and unsupervised learning, convolutional and recurrent neural networks, evolutionary algorithms, and fuzzy logic systems, are reshaping drug discovery pipelines. We explore the role of massive chemical and biological databases such as PubChem, ChEMBL, DrugBank, and the Protein Data Bank, while also highlighting the importance of data quality, curation, and standardization. The integration of computational tools in drug discovery is discussed across key stages-target identification, hit discovery, lead optimization, and de novo molecular design-supported by examples such as AlphaFold, Atomwise, and In silico Medicine. This review aims to offer a holistic understanding of how computational intelligence, when combined with robust data infrastructure, can significantly accelerate the discovery and development of safer, more effective drugs.