Development of fuzzy logic algorithm for predicting heavy metal content in poultry product.

ABSTRACT Temporal images and video segmentation is a difficult task due to noise, occlusions, motion blur and abrupt scene changes. Deep neural networks have shown promise, but their success depends heavily on large amounts of labelled data or pre-training. In contrast, unsupervised clustering avoids this dependence but often suffers from limited robustness. The alternate approach of a meta-heuristic-based clustering algorithm in a dynamic environment is an under-explored area. To address these challenges, a combination of state-of-the-art clustering algorithm, Δ-MOCK (Multi-Objective Clustering with automatic K-determination) and dynamic evolutionary optimization for unsupervised segmentation of temporal images from a scene is proposed. The proposed algorithm Prediction-based Multi-objective Automatic Clustering (PMoAC) begins with superpixel generation and then applies multi-objective optimization to group superpixels based on variance and spatial connectedness. A central feature of PMoAC is a modified Fuzzy Prediction (m-FP) strategy, which extends conventional fuzzy inference by introducing weighted history and adaptive membership weighting to enhance the temporal adaptation. This allows the algorithm to anticipate evolving segmentation and adjust to environmental changes. Comparative experiments on 12 benchmark datasets with different linear and non-linear prediction schemes in the same approach, along with state-of-the-art algorithms: DNSGA-III, DMOEA/D and FDSPEA2-BR show that PMoAC with m-FP achieves consistently higher accuracy and efficiency as illustrated by 31.32 % increase in mean Dice Similarity Coefficient (mDSC), 10.11 % increase in mean hypervolume (mV) with almost 45 % less overall runtime.

Accurate wind power forecasting is essential for enhancing the integration of renewable energy sources, thereby supporting global decarbonization initiatives. However, the inherent stochastic nature of wind resources significantly complicates short-to-medium-term forecasting, introducing operational uncertainties within power systems. Despite substantial improvements in existing forecasting techniques, conventional models often fail to achieve consistently high accuracy, necessitating methodological advancements. To address this limitation, we introduce a novel multi-scale forecasting framework integrating fuzzy information granulation and a multi-objective optimization strategy. The fuzzy information granulation technique effectively captures intrinsic features from highly volatile wind speed data, significantly reducing the data complexity and mitigating noise interference for deep learning models. Moreover, our combined model leverages multiple neural networks employing diverse predictive principles, adaptively integrating their outputs via heuristic optimization algorithms. This approach simultaneously enhances prediction accuracy and robustness. Experimental validation using the Penglai wind farm dataset highlights the outstanding performance of our proposed framework. Importantly, the fuzzy information granulation-based collaborative optimization algorithm effectively resolves the critical trade-off between prediction accuracy and computational efficiency in wind speed forecasting systems.

As the complexity and unpredictability of cyber-physical systems (CPSs) such as multi-agent robotic networks increase, having robust predictive models is crucial for ensuring dependable operations. This paper presents a modification of the Strength Prominence (SP) index, which was initially designed for fuzzy social networks, adapted for use in robotic and intelligent automation systems. The SP index has been reformulated for fuzzy interaction graphs, where nodes signify robotic components and edges represent uncertain communications or dependencies. The modified index assesses link probability by considering the strength of connectedness and prominence levels, even in the absence of common neighbors. Theoretical aspects such as symmetry, boundedness, and monotonicity are thoroughly demonstrated. Empirical validation utilizing real-world datasets and ROS-based robotic data shows that the SP index achieves superior predictive accuracy, surpassing traditional fuzzy indices like CN, RSM, and CAR in terms of precision, AUC, and AUP measurements. This method allows for the early identification of interaction failures, improves the prediction of collaboration, and aids in the development of fault-tolerant designs. This proposed approach provides a new interdisciplinary tool for fuzzy link prediction in CPS, with important implications for the design of autonomous systems, real-time robotic collaboration, and resilient network structures.

Abstract This study presents a comparative evaluation of fuzzy logic-based models for predicting the performance and emission characteristics of a Liquefied Petroleum Gas (LPG)–diesel dual fuel engine (DFE). Fuzzy logic models such as classical fuzzy, Evolving Fuzzy Neural Network (EFuNN), and Adaptive Neuro-Fuzzy Inference System (ANFIS) models were developed and assessed. Models were evaluated using Mean Relative Error (MRE) and prediction accuracy. The ABC-optimized cFCM-RBFNN model outperformed other models in accuracy and compactness and was successfully validated using un-trained data.

Abstract This study proposes a fuzzy neural network-based prediction and optimization method to address the challenge of modeling dynamic stiffness in Stewart platforms. Traditional approaches, such as the Newton-Euler method and finite element analysis, often struggle to capture nonlinear characteristics and multivariate coupling effects under complex conditions. To overcome these limitations, this paper constructs a fuzzy neural network framework that integrates fuzzy logic with neural computation. This model selects drive joint position, velocity, acceleration, torque, and external load as input variables. These inputs are mapped into fuzzy subsets through fuzzification. The fuzzy radial basis function network is designed to simulate the nonlinear relationships between input variables and dynamic stiffness. An error back-propagation algorithm is applied to optimize the network weights, and the structure is refined using cross-validation and grid search. The fuzzy rule base is constructed from both expert knowledge and data-driven insights. Experimental validation is conducted under varying working conditions. This includes load variation and angular velocity changes. The proposed method demonstrates higher accuracy and robustness compared to traditional Newton-Euler, finite element, statistical regression, and reinforcement learning models. The average mean square error under most scenarios is significantly reduced. This paper also highlights the limitations of current fuzzy rule adaptability under unknown disturbances. Future work aims to enhance model generalizability through self-learning mechanisms and simplify computational complexity for real-time applications. Overall, this study contributes a reliable and adaptive approach to improving dynamic stiffness prediction for Stewart platforms, offering insights for broader applications in multi-degree-of-freedom robotic systems.

With the increasing penetration of renewable energy, the frequency regulation burden on thermal power units is growing significantly. Among them, combined cycle gas turbine (CCGT) units are playing an increasingly important role in grid ancillary services due to their high efficiency and low emissions. This paper investigates coordinated control strategies to improve the auxiliary frequency regulation capability of CCGTs, addressing the limitations of traditional control approaches where gas turbines dominate while steam turbines respond passively. A decentralized model predictive control (MPC) strategy based on rate-limited signal decomposition is proposed to improve auxiliary frequency regulation. First, a dynamic model of the F-class CCGT systems oriented towards control is established. Then, predictive controllers are designed separately for the top and bottom cycles, with control accuracy improved through a fuzzy prediction model, Kalman filtering and state augmentation. Furthermore, a multi-scale decomposition method for AGC (Automatic Generation Control) signals is developed, separating the signals into load-following and high-frequency components, which are allocated to the gas and steam turbines respectively for coordinated response. Comparative simulations with a conventional MPC strategy demonstrate that the proposed method significantly improves power tracking speed, stability, and overshoot control, with the IAE (Integral of Absolute Error) index reduced by 83.7%, showing strong potential for practical engineering applications.

Tsunamis are among the most terrifying natural hazards, causing significant loss of life and property and impacting our society’s human, economic, and social aspects. Given their destructive nature, developing effective techniques for tsunami observation and demolition reduction is crucial. This study proposes a novel tsunami detection and alert system utilizing fuzzy logic to mitigate these impacts. The primary objective of this research is to develop and implement a fuzzy logic-based tsunami prediction system that generates alerts indicating the likelihood of a tsunami-categorized as definite, certain, average, or rare. In the present study, we employ the fuzzy logic technique in MATLAB, using various defuzzification techniques available in the MATLAB fuzzy logic toolbox. The calculated values for the tsunami alert system in the Makran Subduction Zone are as follows: rare (1.91), average (4.75), certain (6.75), and definite (8.8). The designed tsunami alert system and model can predict tsunamis automatically and manually, potentially saving many lives more effectively than previous methods. The research objectives of this study are to (1) develop a fuzzy logic-based model for tsunami prediction, (2) implement the model using MATLAB, and (3) evaluate the model’s performance in generating accurate tsunami alerts.

Fuzzy Logic-Based Prediction of Probability of Infection in Mahakal Ujjain Temple, India: Enhancing Ventilation Strategies for Public Health Safety

Abstract Financial markets have a profound impact on societal well-being, influencing household net financial wealth, particularly pension-related assets. Events like as the 2007 financial crisis, Covid-19 outbreak, the Russia-Ukraine war, and oil price shocks, also contribute to extreme price fluctuations. These wealth losses not only affect households’ economic behavior (e.g., employment, retirement planning, consumption, and investment), but also have implications for social behavior (e.g., intergenerational transfers) and mental health. Time series analysis is a powerful tool for understanding the dynamics of stock prices over time and predicting future behavior. However, the inherent uncertainty and ambiguity in time series data pose challenges for traditional statistical models. In order to address this specific problem, this study proposes an Artificial Intelligence (AI)-driven approach utilizing fuzzy time series modeling integrated with fuzzy clustering, information granules, picture fuzzy sets and new defuzzification rules. The linguistic values of market historical data are described by capturing the positive, neutral, and negative aspects of each observation through the application of picture fuzzy sets. This AI-enhanced approach incorporates a new method for partitioning the reorganized universe of discourse into intervals using the fuzzy c-means clustering and data granulation, and a novel membership function, composed of three Gaussian functions is defined to assign picture fuzzy memberships to each interval. Additionally, the proposed model employs a picture fuzzy weighted aggregation operator to aggregate the membership information across a multiple picture fuzzy sets, and use a rule-based method for defuzzifying the picture fuzzy sets to obtain crisp forecasts. The proposed model is evaluated on the TAIEX dataset and compared with several existing fuzzy time series prediction methods in terms of standard accuracy measures. The results demonstrated that the proposed approach outperforms existing techniques, providing more accurate and reliable forecasts. Furthermore, the model highlights the potential to offer more information and insights for decision-making and analysis in financial contexts through multivariate picture fuzzy modeling.

Solving dynamic multi-objective engineering design problems via fuzzy c-means prediction algorithm

Accurate prediction of system degradation and remaining useful life (RUL) is essential for reliable health monitoring of Lithium-ion (Li-ion) batteries, as well as other dynamic systems. While evolving systems can offer adequate adaptability to the nonstationary and nonlinear behavior of battery degradation, existing methods often face challenges such as uncontrolled rule growth, limited adaptability, and reduced accuracy under noisy conditions. To address these limitations, this paper presents a smart evolving fuzzy predictor with customized firefly optimization (SEFP-FO) to provide a better solution for battery RUL prediction. The proposed SEFP-FO technique introduces two main contributions: (1) An activation- and distance-aware penalization strategy is proposed to govern rule evolution by evaluating the structural relevance of incoming data. This mechanism can control rule growth while maintaining model convergence. (2) A customized firefly algorithm is suggested to optimize the antecedent parameters of newly generated fuzzy rules, thereby enhancing prediction accuracy and improving the predictor’s adaptive capability to time-varying system conditions. The effectiveness of the proposed SEFP-FO technique is first validated by simulation using nonlinear benchmark datasets, which is then applied

A novel career prediction method based on fuzzy model-Fuzzy clustering approach.

Fine-grained image classification tasks face challenges such as difficulty in labeling, scarcity of samples, and small category differences. To address this problem, this study proposes a novel fine-grained image classification method based on the MogaNet network and a multi-level gating mechanism. A feature extraction network based on MogaNet is constructed, and multi-scale feature fusion is combined to fully mine image information. The contextual information extractor is designed to align and filter more discriminative local features using the semantic context of the network, thereby strengthening the network’s ability to capture detailed features. Meanwhile, a multi-level gating mechanism is introduced to obtain the saliency features of images. A feature elimination strategy is proposed to suppress the interference of fuzzy class features and background noise. A loss function is designed to constrain the elimination of fuzzy class features and classification prediction. Experimental results demonstrate that the new method can be applied to 5-shot tasks across four public datasets: Mini-ImageNet, CUB-200-2011, Stanford Dogs, and Stanford Cars. The accuracy rates reach 79.33, 87.58, 79.34, and 83.82%, respectively, which shows better performance than other state-of-the-art image classification methods.

Thermal behaviour analysis of a solar air heater with thermal energy storage: experimental study and Takagi-Sugeno Neuro fuzzy model prediction

Flooding is one of the natural disasters that frequently occurs in Indonesia, causing material losses and loss of life. To support early warning systems and risk mitigation, accurate flood prediction is needed. This study focuses on applying the Tsukamoto fuzzy logic method to predict flood potential in the Blitar Regency. The choice of this method is based on its ability to handle data uncertainty and produce more accurate predictions through the rule-based defuzzification process. The main variables analyzed include rainfall, river discharge, and regional characteristics that influence the likelihood of flooding. The results of the study show that the Tsukamoto fuzzy logic method can predict flood potential with a high level of accuracy, which is in line with findings from previous studies. It is hoped that this fuzzy logic-based prediction system can provide an effective solution for early warning, reduce the impact of flooding, and support decision-making in flood disaster mitigation in the Blitar Regency.

Semi-tensor product-based fuzzy relation matrix technique for gear system state forecasting.

Abstract Single weld beads were deposited on a steel plate using three different welding wire feed rates (slow, medium, and fast). The samples were preheated before welding at three different temperatures (100, 150, and 200°C). Fuzzy logic models were developed and integrated into the analysis for predicting weld bead geometries. The experimental results demonstrated that preheating and wire feed rates had significant impact on the geometric shape characteristics of 1020 weld beads. Higher preheating temperatures and optimal wire feed rates led to improved weld bead geometry. The integrated fuzzy logic model predicted the weld bead geometry with optimal input variables of 23 V, 150 A, 3 mm/s welding speed, and 540 J/mm heat input, with an optimal bead width, bead height, depth of penetration, heat affected zone (HAZ) width, and height (9.72, 2.02, 1.62, 12.54 and 2.73 mm). The accuracy of the fuzzy models were examined via regression plots, which yielded R 2 values of 0.9146, 0.9909, 0.9467, 0.9805, and 0.8239, for the bead width, bead height, depth of penetration as well as HAZ width and height. This implies that the fuzzy models were effective in predicting the bead height, justifying from its very high degree R 2 value of 0.9909. This showcased the viability of fuzzy logic for predicting weld bead geometry.

The non-invasive assessment of central lymph node metastasis (CLNM) in patients with papillary thyroid carcinoma (PTC) plays a crucial role in assisting treatment decision and prognosis planning. This study aims to use an interpretable deep fuzzy network guided by expert knowledge to predict the CLNM status of patients with PTC from ultrasound images. A total of 1019 PTC patients were enrolled in this study, comprising 465 CLNM patients and 554 non-CLNM patients. Pathological diagnosis served as the gold standard to determine metastasis status. Clinical and morphological features of thyroid were collected as expert knowledge to guide the deep fuzzy network in predicting CLNM status. The network consisted of a region of interest (ROI) segmentation module, a knowledge-aware feature extraction module, and a fuzzy prediction module. The network was trained on 652 patients, validated on 163 patients and tested on 204 patients. The model exhibited promising performance in predicting CLNM status, achieving the area under the receiver operating characteristic curve (AUC), accuracy, precision, sensitivity and specificity of 0.786 (95% CI 0.720-0.846), 0.745 (95% CI 0.681-0.799), 0.727 (95% CI 0.636-0.819), 0.696 (95% CI 0.594-0.789), and 0.786 (95% CI 0.712-0.864), respectively. In addition, the rules of the fuzzy system in the model are easy to understand and explain, and have good interpretability. The deep fuzzy network guided by expert knowledge predicted CLNM status of PTC patients with high accuracy and good interpretability, and may be considered as an effective tool to guide preoperative clinical decision-making.

It is recognized that the use of centrifugal gravity concentrators is more effective than conventional concentrators in recovering fine-grained coal tailing. In the Knelson concentrator study, fuzzy logic was used to investigate the prediction of ash content and combustible recovery. The Western Lignite Company (WLC) tailing sample was classified into -1+0.038, -1+0.212 and 0.212+0.038 mm size groups. In the prediction studies, centrifugal force (20, 30, 40 and 50 G) and flow rate (2, 3 and 4 L/min) were used as input variables. Then the results of the fuzzy logic prediction were compared with the actual values and found that the fuzzy logic system could be successfully applied to the Knelson concentrator enrichment results.