Image segmentation plays a crucial role in medical imaging, remote sensing, and object detection. However, challenges persist due to uncertainty in region classification, sensitivity to noise, and discontinuities in object boundaries. To address these issues, a novel segmentation framework is proposed, integrating Complex Pythagorean Fuzzy Aggregation Operators (CPFAs) with a level-set-based optimization strategy to enhance both precision and adaptability. The proposed model leverages complex Pythagorean fuzzy membership functions, incorporating both magnitude and phase components, to effectively manage overlapping intensity distributions and classification uncertainty. Additionally, geometric constraints, including gradient and curvature-based regularization, are employed to refine boundary evolution, ensuring accurate edge delineation in noisy and complex imaging conditions. A key contribution of this work is the formulation of a complex fuzzy energy functional, which synergistically integrates fuzzy region classification, phase-aware boundary refinement, and geometric constraints to guide segmentation. The level-set method is utilized to iteratively minimize this functional, facilitating smooth transitions between segmented regions while preserving structural integrity. Experimental evaluations conducted across diverse imaging domains demonstrate the robustness and versatility of the proposed approach, highlighting its efficacy in medical image segmentation, remote sensing analysis, and object detection. The integration of complex fuzzy logic with geometric optimization not only enhances segmentation accuracy but also improves resilience to noise and irregular boundary structures, making this framework particularly suitable for applications requiring high-precision image analysis.
Transformer-based language models have demonstrated remarkable success in few-shot text classification; however, their effectiveness is often constrained by challenges such as high intraclass diversity and interclass similarity, which hinder the extraction of discriminative features. To address these limitations, a novel framework, Adaptive Masking Bidirectional Encoder Representations from Transformers with Dynamic Weighted Prototype Module (AMBERT-DWPM), is introduced, incorporating adaptive masking and dynamic weighted prototypical learning to enhance feature representation and classification performance. The standard BERT architecture is refined by integrating an adaptive masking mechanism based on Layered Integrated Gradients (LIG), enabling the model to dynamically emphasize salient text segments and improve feature discrimination. Additionally, a DWPM is designed to assign adaptive weights to support samples, mitigating inaccuracies in prototype construction caused by intraclass variability. Extensive evaluations conducted on six publicly available benchmark datasets demonstrate the superiority of AMBERT-DWPM over existing few-shot classification approaches. Notably, under the 5-shot setting on the DBpedia14 dataset, an accuracy of 0.978±0.004 is achieved, highlighting significant advancements in feature discrimination and generalization capabilities. These findings suggest that AMBERT-DWPM provides an efficient and robust solution for few-shot text classification, particularly in scenarios characterized by limited and complex textual data.
Accurate estimation of tree height is fundamental to sustainable forest management, particularly in regions such as Kumrat Valley, Pakistan, where Deodar Cedar (Cedrus deodara) serves as a vital ecological and economic resource. Conventional height estimation models often exhibit limitations in capturing the inherent complexity of forest ecosystems, where multiple environmental factors interact non-linearly. To address this challenge, a hybrid predictive framework integrating fuzzy inference systems (FIS) and multiple linear regression (MLR) has been developed to enhance the accuracy of height estimation. The FIS model incorporates key environmental and physiological parameters, including trunk diameter, soil quality, temperature, and rainfall, which are classified into fuzzy sets—low, medium, and high—corresponding to distinct growth rates (slow, normal, fast) and developmental stages (early, average, late). This classification enables a nuanced representation of environmental variability and tree growth dynamics. Complementarily, the MLR model quantifies the statistical relationships between these variables and tree height, yielding an R² value of 0.85, an adjusted R² of 0.64, and a statistically significant p-value of 0.04. The integration of fuzzy logic with regression analysis offers a robust, data-driven approach to height prediction, effectively addressing the uncertainties associated with environmental fluctuations. By leveraging both rule-based inference and quantitative modeling, this method provides valuable insights for precision forestry, contributing to the sustainable management and conservation of Deodar Cedar in Kumrat Valley.
With the rapid advancement of modern robotics and artificial intelligence, intelligent picking robots have been widely adopted in agricultural production. Global path planning techniques have been applied to crop harvesting, such as oranges, apples, tea leaves, and tomatoes, yielding promising results. This study focuses on the path planning problem for a robotic arm used in premium tea leaf picking. Experimental simulations reveal that the Ant Colony Optimization (ACO) algorithm performs particularly well in solving small-scale Traveling Salesman Problems (TSP), as it can incrementally construct initial paths and, with properly tuned parameters, produce higher-quality solutions and achieve faster convergence compared to other algorithms. However, the traditional ACO algorithm tends to fall into local optima and suffers from slow convergence. To address these challenges, this paper proposes a dynamically optimized ACO algorithm that enhances the pheromone update rules and optimizes the $\alpha$ and $\beta$ parameters during the search process. These parameters are updated according to the optimization results, and a ranking factor is introduced to prevent the optimal picking path from being overlooked. The proposed method demonstrates superior performance over the traditional ACO algorithm in terms of path quality and convergence speed.
This research examines customer relationship management (CRM) systems using multi-criteria decision-making (MCDM) methods, with the intention of selecting the most suitable solution for small companies. The main goal of this research is to make a decision when choosing a CRM system by applying an objective approach. For this purpose, objective criteria were used, and an objective evaluation of the observed CRM systems was conducted. By using the MEREC (MEthod based on the Removal Effects of Criteria) method, the importance of the criteria was determined, while the CORASO (COmpromise Ranking from Alternative SOlutions) method was applied to rank the CRM systems. These methods were combined using a methodology into a hybrid approach. The results of this approach indicate that CRM systems with a higher degree of integration and automation achieved a higher rank, while systems with limited functionalities and longer implementation times received a lower ranking. This analysis confirms the importance of CRM systems in optimizing business processes, improving customer satisfaction, and enhancing marketing activities in companies. The results of the research can assist small companies in making decisions when selecting a CRM system. The contribution of this research is to provide efficient decision-making in the selection of a CRM system, thereby strengthening the companies' operations and improving their performance.
As a critical component of mechanical transmission systems, gears play a vital role in ensuring industrial production runs smoothly. Undetected gear failures can lead to mechanical breakdowns, production interruptions, and even safety hazards. Therefore, an efficient gear fault detection method is essential for maintaining industrial continuity and safety. This paper proposes a hybrid model that integrates convolutional neural networks (CNN) and support vector machines (SVM) for gear fault detection. The model leverages CNNs to automatically extract key features from vibration signals, while SVMs enhance classification accuracy, resulting in a high-precision fault diagnosis system. On a publicly available gear fault dataset, the proposed model achieved an impressive accuracy of 0.9922, significantly outperforming single-classifier models. Moreover, the model exhibits a short training time, demonstrating its computational efficiency. This research provides an effective and automated approach to gear fault detection, offering significant potential for industrial applications.
The objective of this work is to analyze the environmental sustainability performance of deposit banks traded in Borsa Istanbul (BIST) through the application a novel integrated grey Multi-Criteria Decision-Making (MCDM) approach. The grey combined model proposed for the assessment of environmental performance in the banking sector integrates the Logarithmic Objective Weighting Based on Percentage Change (LOPCOW) and Proximity Indexed Value (PIV) algorithms. In the first stage, the importance weights of the criteria were determined using the Grey LOPCOW objective weighting technique, which enables a comprehensive and robust weighting system. Following this, the Grey PIV method was employed to assess the banks' environmental sustainability performance. To demonstrate the robustness and applicability of the suggested MCDM framework, several sensitivity analyses and comparative assessments were conducted. The empirical findings imply that the most significant environmental performance indicator affecting the environmental sustainability performance of deposit banks is “amount of disposed waste”. Moreover, Yapı Kredi was identified to be the bank with the highest environmental sustainability performance compared to its competitors in the BIST banking industry. The findings obtained through sensitivity and comparative analyses indicate that the introduced hybrid decision model in the existing work constitutes a robust, defendable, and effective framework for assessing the environmental sustainability performance of banking institutions. Lastly, the findings have important implications for bank management, regulators, and policymakers, offering valuable insights for the enhancement of sustainability practices within the banking industry. This work contributes to the growing body of literature on environmental performance measurement in the financial sector and provides a methodological foundation for future sustainability assessments in similar contexts.
This study addresses the issues of fragmentation, unstructured information, and low reusability in the process knowledge management of aircraft engine component manufacturing. A process knowledge modeling method based on ontology is proposed. By constructing an ontology knowledge base tailored for the aircraft engine manufacturing domain, an improved top-down approach is employed. This method introduces feature-based constraints on process parameters and uses tools to create a Web Ontology Language (OWL) model. The manufacturing of a long tension bolt is chosen as the case study, and application verification is carried out based on the Model-Based Definition (MBD) model. The results demonstrate that the proposed method significantly improves the sharing and reusability of process knowledge, providing theoretical support for the intelligent process design of aircraft engine components.
The theory of Complex T-Spherical Fuzzy Sets (CTSpFSs) is introduced along with their Einstein operational methods under induced variables. This research aims to extend the theoretical framework of complex fuzzy sets (CFSs) by exploring fundamental Einstein operational laws and proposing two novel aggregation operators: the induced complex T-spherical fuzzy Einstein ordered weighted averaging (I-CTSpFEOWA) operator and the induced complex T-spherical fuzzy Einstein hybrid averaging (I-CTSpFEHA) operator. Aggregation operators serve as powerful tools in data analysis, decision-making, and understanding complex systems by enabling the extraction of meaningful insights from large, multidimensional datasets. These operators contribute to the simplification of information, ultimately enhancing decision support in complex decision-making processes. The proposed operators, designed to handle complex and multidimensional fuzzy information, enhance the ability to refine these decision-making processes. Their effectiveness is demonstrated through the development of a numerical example, which illustrates their potential application in real-world scenarios. The proposed techniques not only improve the clarity and relevance of the aggregated information but also provide an efficient methodology for managing complex fuzzy environments, thus refining decision-making across diverse domains. By demonstrating the utility of the I-CTSpFEOWA and I-CTSpFEHA operators, the research highlights their practical application in systems where traditional fuzzy aggregation methods may fall short. This work contributes significantly to the field of fuzzy set theory by presenting advanced aggregation methods that support improved decision-making in environments characterised by uncertainty and complexity.
In recent years, e-commerce has emerged as a dominant sales channel, with an increasing number of large-scale companies exclusively operating online. The substantial growth of e-commerce has been paralleled by the growing importance of efficient logistics, as the flow of goods in international trade demands sophisticated planning and execution. Following the purchase stage, logistics plays a pivotal role in ensuring timely delivery to end customers, with final distribution being one of the most critical aspects. The optimization of the distribution process is particularly challenging due to the complexities involved in the selection of transport modes, optimal routing, and the appropriate types of vehicles. This study investigates the parcel distribution process in the Serbian logistics sector, providing a comprehensive analysis of e-commerce flows during the initial stages of goods movement. A decision-making model based on the Stepwise Weight Assessment Ratio Analysis (SWARA) and Weighted Aggregated Sum Product Assessment (WASPAS) methods is proposed to optimize vehicle selection for parcel distribution. The model evaluates ten vehicle alternatives across nine distinct criteria: delivery volume ($\mathrm{C}_1$), average number of parcels per delivery ($\mathrm{C}_2$), vehicle fleet size ($\mathrm{C}_3$), payload capacity ($\mathrm{C}_4$), number of customer complaints ($\mathrm{C}_5$), cargo volume ($\mathrm{C}_6$), incidence of damaged shipments ($\mathrm{C}_7$), loss of shipments ($\mathrm{C}_8$), and vehicle height limitations ($\mathrm{C}_9$). Sensitivity analysis is conducted to test the robustness and stability of the proposed model, ensuring that the selected vehicle configurations are resilient under varying operational conditions. The findings contribute to the broader understanding of logistics optimization in e-commerce, offering insights into the effective selection of transport vehicles that can enhance the efficiency and reliability of the final distribution phase.
Urban competitiveness is an essential determinant of the long-term sustainability and economic development of cities, influencing not only local prosperity but also national growth. The accurate measurement of urban competitiveness is critical for policymakers, as it provides insights into the strengths and weaknesses of cities, informing strategic development. This study evaluates the competitiveness of 17 European cities through an integrated Multi-Criteria Decision-Making (MCDM) framework, combining the Logarithmic Percentage Change-driven Objective Weighting (LOPCOW) method for criteria weighting with the Ranking of Alternatives with Weights of Criterion (RAWEC) method for city ranking. The dataset utilised in this analysis was derived from the 2024 Global Power City Index (GPCI), a comprehensive report assessing various urban performance dimensions. The LOPCOW methodology revealed that the livability (L) criterion holds the highest weight in determining urban competitiveness, whereas research and development (R&D) emerged as the least influential factor. Using the RAWEC method, cities were ranked based on their overall competitiveness, with London identified as the most competitive urban centre, while Istanbul was ranked lowest. The findings highlight the importance of livability in enhancing urban competitiveness and suggest that cities should prioritise improvements in R&D to foster more balanced and sustainable competitiveness. This research contributes to the growing body of literature on urban performance measurement, offering a novel methodological approach that integrates both objective weighting and ranking techniques, which can be applied to further studies on global urban competitiveness.