Search Results (669)

Digital Transformation (DTN) and Social Media Use (SMU) are reshaping how firms pursue competitiveness and sustainability. Yet, their combined effects on Sustainable Business Performance (SBP)—particularly in emerging-market retail contexts—remain insufficiently explored. This study contributes to closing this gap by exploring how DTN and SMU jointly enhance SBP through interrelated organizational capabilities: Collaboration Networks (CNS), Service Innovation (SIN), Customer Experience (CEX), Organizational Resilience (ORE), and Competitive Advantage (CAE). A dual-method design was adopted. In Phase 1, twenty-three experts participated in a three-round electronic Delphi (e-Delphi) process, during which Fuzzy C-Means (FCM) clustering was used to refine forty-seven indicators and validate expert consensus. The integration of e-Delphi and FCM clustering introduces a novel approach to consensus validation, enhancing methodological rigor. In Phase 2, survey data from 982 Thai retail executives were evaluated employing Confirmatory Factor Analysis (CFA) and Structural Equation Modeling (SEM). The results revealed that DTN and SMU significantly improve SBP when mediated by SIN, CEX, and ORE. Specifically, SMU fosters CNS and SIN, whereas DTN strengthens CEX and CAE. Theoretically, this study integrates the Resource-Based View (RBV) and Dynamic Capabilities Theory (DCT); empirically, it provides rare large-scale evidence from Thailand’s retail industry; and practically, it positions DTN as a driving force behind innovation, resilience, and inclusive development consistent aligned with the United Nations Sustainable Development Goals (SDGs). Full article

The detection of exoplanets in space-based photometry relies on identifying periodic transit signatures in stellar light curves. The Kepler Threshold Crossing Events (TCE) catalog collects all periodic dimming signals detected by the pipeline, while the Kepler Objects of Interest (KOI) catalog provides vetted dispositions (CONFIRMED, CANDIDATE, FALSE POSITIVE). However, the pathway from raw TCE detections to KOI classifications remains ambiguous in many borderline cases. We introduce FAS-XAI, a framework that integrates Fuzzy C-Means (FCM) clustering, supervised learning, and explainable AI (XAI) to improve transparency in exoplanet candidate classification. FCM applied to TCE parameters (period, duration, depth, and SNR) reveals three meaningful regimes in the transit-signal space and quantifies ambiguity through fuzzy memberships. Linking these clusters to KOI dispositions highlights a progressive consolidation of confirmed planets within the high-SNR, medium-duration regime. A supervised XGBoost classifier trained on KOI labels and augmented with fuzzy memberships achieves strong performance (Accuracy = 0.73, Macro F1 = 0.69, ROC–AUC = 0.855), clearly separating CONFIRMED and FALSE POSITIVE objects while appropriately reflecting the transitional nature of CANDIDATES. SHAP, LIME, and ELI5 provide consistent global and local attributions, identifying period, duration, depth, SNR, and fuzzy ambiguity as the key explanatory features. Finally, stellar parameters from Kepler DR25 validate the physical plausibility of the detected regimes, demonstrating that FAS-XAI captures astrophysically meaningful patterns rather than purely statistical structures. Overall, the framework illustrates how fuzzy logic and explainable AI can jointly enhance the interpretability and scientific rigor of exoplanet vetting pipelines. Full article

Thermal error is a significant factor affecting the machining accuracy of machine tools, and error compensation is an economical and effective method to improve machine tool accuracy. However, traditional modeling methods face challenges such as insufficient nonlinear mapping capability and difficulty in parameter optimization when processing time-series data. This paper establishes a thermal error model using a Long Short-Term Memory (LSTM) neural network optimized by the Particle Swarm Optimization (PSO) algorithm (PSO-LSTM). Through thermal characteristic experiments, thermal error data and temperature rise data at various points of the T55II-500 CNC machine tool during actual machining were collected. First, fuzzy clustering and global sensitivity analysis were employed to identify the temperature-sensitive points of the machine tool. Using the temperature rise data of these sensitive points and the thermal errors of machined workpieces as data samples and optimizing the LSTM prediction model with the PSO algorithm, a PSO-LSTM thermal error prediction model was established. To verify its superiority and practicality, this paper conducts a comparative analysis with traditional thermal error prediction models based on Backpropagation (BP) neural network, Long Short-Term Memory (LSTM) network, Multiple Linear Regression (MLR), and Multivariate Nonlinear Regression (MNR). The results show that the PSO-LSTM model outperforms the other models in terms of relative error, average residual, maximum residual, and mean squared error. On this basis, a real-time thermal error compensation system was developed. Under the conditions of near-constant temperature (19.34–20.36 °C), warm natural ventilation (20.63–22.13 °C), and a wider variable temperature range (18.64–28.24 °C), the compensated thermal errors converge from 52 μm, 57 μm, and 67 μm to 4–12 μm, 6–11 μm, and 5–9 μm, respectively, with precision improved by 86%, 88%, and 86%. This effectively reduces the impact of thermal errors and improves the machining accuracy of the machine tool. Full article

Chlorophyll-a (Chl-a) concentration is a key parameter for assessing the degree of eutrophication and the algal bloom risk in water bodies. Accurate and robust monitoring of Chl-a is crucial for effective water quality management of inland and coastal optically complex Case-II waters. This study proposes a stratified integrated framework that combines optical water type (OWT) classification and multi-index blending models and evaluates the capability of ZY-1 02E hyperspectral imagery in the retrieval of Chl-a concentration in Case-II waters. This research is based on ZY-1 02E hyperspectral remote sensing images and ground synchronous measurement data from four typical water bodies in China (Dongpu Reservoir, Nanyi Lake, Tangdao Bay, and Moon-lake Reservoir). Using Fuzzy C-Means (FCM) clustering combined with spectral feature analysis, three different OWTs were identified, and the bands sensitive to Chl-a for each water type were recognized. Subsequently, the most suitable semi-empirical indices (BR, TBI) were selected, and a new suspended matter correction index (SMCI) was constructed by integrating spectral bands and TSM data specifically for high-turbidity waters to facilitate the retrieval of Chl-a concentration. The RMSE and MAPE of the model constructed based on the unclassified dataset were 3.1586 μg·L⁻¹ and 30.82%, respectively. When the stratified ensemble method based on optical water type classification was employed, the overall RMSE and MAPE were reduced to 1.5832 μg·L⁻¹ and 16.36%. The results demonstrate that this hierarchical ensemble framework significantly improved the retrieval accuracy of Chl-a concentration. An uncertainty assessment of the Chl-a retrieval model for highly turbid waters incorporating SMCI was conducted using the Monte Carlo method, revealing a mean coefficient of variation of 0.0567 and a coverage rate of 95.65% for the 95% confidence interval, indicating high predictive stability and reliability of the model. This study emphasizes the importance of the integrated framework strategy that combines OWTs classification and multi-index blending models for accurate and robust remote sensing estimation of Chl-a concentration under optically complex environmental conditions. It confirms the application potential of ZY-1 02E hyperspectral data in monitoring Chl-a in inland and near-coastal waters at medium and small scales. Full article

To address the issues of high labor intensity, high missed harvest rates, and high damage rates associated with traditional subsurface crop harvesters, this paper takes carrots as the research object and designs an automatic row-following device based on collaborative perception and intelligent control. Firstly, the physical characteristic parameters and planting agronomic requirements of carrots in a harvest period were systematically measured and analyzed, and a collaborative control architecture with ‘lateral row-following and longitudinal profiling’ as the core was established. The architecture was composed of a lateral detection mechanism and a ridge surface floating detection mechanism. Building on this, this paper designed a control system with a STC12C5A60S2 single-chip microcomputer as the control core and a fusion fuzzy PID algorithm. By collaboratively driving the lateral and vertical stepper motors, the system achieved a precise control of the digging device’s position and posture, significantly improving the response speed and control stability under complex ridge conditions. Through the simulation of SolidWorks (2019) and RecurDyn (2023), the structural reliability and dynamic profiling effect of key components were validated from both static and dynamic perspectives, respectively. The parameter optimization results based on the response surface method show that the lateral motor speed and the forward speed are the dominant factors affecting the lateral accuracy and the vertical accuracy, respectively. Under the optimal parameter combination, the mean lateral deviation of the device measured in the field test was 1.118 cm, and the standard deviation was 0.257 cm. The mean vertical deviation is 0.986 cm, and the standard deviation is 0.016 cm. This study provides a feasible technical solution for the mechanized agronomic operation of carrots and other subsurface crops. Full article

Understanding traffic congestion in urban areas is crucial for ensuring mobility, especially in metropolitan cities of developing countries. This study presents new spatial and temporal data to analyze congestion in Casablanca. Spatial data, collected using QGIS, covers 22 ZIP code areas and includes built environment factors such as land use, road types, and public transport stations. Temporal data consists of 440 randomly generated trajectories per commune, with real-time travel data collected hourly over one week using the Waze Route Calculator. A Python script was used to compute the Travel Time Index (TTI) for each zone. To classify zones based on congestion patterns, we applied fuzzy c-means clustering, allowing for nuanced grouping and interpretation of overlapping characteristics. This dataset supports traffic modeling, simulation, and congestion analysis in developing urban contexts. Full article

To ensure end-to-end Quality of Service (QoS) management in 5G-TSN converged networks, this paper proposes a dynamic weighted QoS mapping method based on Weighted Fuzzy C-Means and Three-Way Decisions (WFCM-TDwQM). The WFCM algorithm is employed to cluster Time-Sensitive Networking (TSN) flows based on their QoS attributes, reducing computational complexity. A three-way decision-based method is used to assign a reasonable and approximate set of 5G QoS Identifier (5QI) values to each cluster. Finally, dynamic weights are adjusted by considering QoS similarity and the residual load rate, enabling the system to adapt to network load changes. The experimental results show that, compared with three other mapping algorithm combinations, WFCM-TDwQM not only ensures end-to-end QoS consistency but also achieves better load balancing under varying network loads. Moreover, its mapping performance is evaluated under different network scenarios. Full article

Typhoons pose severe threats to coastal regions through destructive winds and extreme rainfall, with rainfall-induced flooding often causing more casualties and economic damage than wind damage alone. Accurate precipitation forecasting is therefore paramount for effective disaster risk management. This study proposes a trajectory-based framework for predicting cumulative rainfall from typhoon events, based on the premise that cyclones with similar tracks yield comparable precipitation due to topographic interactions. An extensive dataset of typhoons over East Asia (1979–2022) is analyzed, and two new similarity metrics—the Kernel Density Similarity Index (KDSI) and the Comprehensive Index (CI)—are introduced to quantify track resemblance. Their predictive skill is benchmarked against existing indices, including fuzzy C-means, convex hull area, and triangle mesh methods. Optimal performance is achieved using an ensemble of 13 analogous cyclones, which minimizes root-mean-square error (RMSE). Validation across a large sample demonstrates that the proposed model overcomes limitations of earlier approaches, providing a robust and efficient tool for forecasting typhoon-induced rainfall. Full article

Turbidity is a crucial and reliable indicator that is extensively utilized in water quality monitoring through remote sensing technology. The development of accurate and applicable models for turbidity estimation is essential. While many existing studies rely on uniform models based on statistical regression or traditional machine learning techniques, the application of deep learning models for turbidity estimation remains limited. This study proposed deep learning models for turbidity estimation based on optical classification of inland waters using Sentinel-2 data. Specifically, the fuzzy c-means (FCM) clustering method was employed to classify optical water types (OWTs) based on their spectral reflectance characteristics. A weighted sum of the turbidity prediction results was generated by the OWT-based convolutional neural network-random forest (CNN-RF) model, with weights derived from the FCM membership degrees. Turbidity for four typical waters was mapped by the proposed method using Sentinel-2 images. The FCM method efficiently classified waters into three OWTs. The OWT-based weighted CNN-RF model demonstrated strong robustness and generalization performance, achieving a high prediction accuracy (R² = 0.900, RMSE = 11.698 NTU). The turbidity maps preserved the spatial continuity of the turbidity distribution and accurately reflected water quality conditions. These findings facilitate the application of deep learning models based on optical classification in turbidity estimation and enhance the capabilities of remote sensing for water quality monitoring. Full article

The sine cosine algorithm (SCA) is a population-based stochastic optimization method that updates the position of each search agent using the oscillating properties of the sine and cosine functions to balance exploration and exploitation. While flexible and widely applied, the SCA often suffers from premature convergence and getting trapped in local optima due to weak exploration–exploitation balance. To overcome these issues, this study proposes a multi-faceted SCA (MFSCA) incorporating several improvements. The initial population is generated using dynamic opposition (DO) to increase diversity and global search capability. Chaotic logistic maps generate random coefficients to enhance exploration, while an elite-learning strategy allows agents to learn from multiple top-performing solutions. Adaptive parameters, including inertia weight, jumping rate, and local search strength, are applied to guide the search more effectively. In addition, Lévy flights and adaptive Gaussian local search with elitist selection strengthen exploration and exploitation, while reinitialization of stagnating agents maintains diversity. The developed MFSCA was tested against 23 benchmark optimization functions and assessed using the Wilcoxon rank-sum and Friedman rank tests. Results showed that MFSCA outperformed the original SCA and other variants. To further validate its applicability, this study developed a fuzzy c-means MFSCA-based adaptive neuro-fuzzy inference system to forecast energy consumption in student residences, using student apartments at a university in South Africa as a case study. The MFSCA-ANFIS achieved superior performance with respect to RMSE (1.9374), MAD (1.5483), MAE (1.5457), CVRMSE (42.8463), and SD (1.9373). These results highlight MFSCA’s effectiveness as a robust optimizer for both general optimization tasks and energy management applications. Full article

Air source heat pumps (ASHPs) have become a promising alternative to conventional heating and cooling systems, making accurate performance prediction increasingly important. This study presents a comparative analysis of Adaptive Neuro-Fuzzy Inference System (ANFIS) and Artificial Neural Network (ANN) models for evaluating the ASHP performance under varying ambient conditions, examining the symmetry or asymmetry of prediction behavior across cold and hot regimes. Two experimental campaigns were carried out in a controlled climate room: the first primarily covering moderate to high temperatures ($-3 °\mathrm{C}$ to $36 °\mathrm{C}$), and the second mainly covering negative and low ambient temperatures ($-16 °\mathrm{C}$ to $18 °\mathrm{C}$). Performance data were collected to capture system behavior under diverse thermal conditions, making predictions more challenging. Both models were optimized, ANFIS through grid partitioning and ANN via architecture selection. Results demonstrate that ANN models achieved a superior overall accuracy, with mean absolute errors of 0.061 to 0.064 for cold and hot ambient conditions, respectively, showing a particularly strong performance under cold conditions. ANFIS demonstrated remarkable robustness in low-temperature predictions, maintaining less than 3% deviation across variations in water inlet temperature. Both approaches revealed temperature-dependent characteristics: cold-condition modeling required more complex architectures but yielded higher precision, whereas warm-condition modeling performed reliably with simpler configurations but showed slightly reduced accuracy. Full article

The classification of urban residential settlements through Machine Learning (ML) and Deep Learning (DL) remains a complex task due to the intrinsic heterogeneity of urban environments and the scarcity of large, accurately labeled training datasets. To overcome these limitations, this study introduces a novel GIS-based unsupervised classification framework that exploits Fuzzy C-Means (FCM) clustering for the detection and interpretation of urban morphologies. Compared to unsupervised classification approaches that rely on crisp-based clustering algorithms, the proposed FCM-based method more effectively captures heterogeneous urban fabrics where no clear predominance of specific building types exists. Specifically, the method applies fuzzy clustering to census units—considered the fundamental scale of urban analysis—based on construction techniques and building periods. By grouping census areas with similar structural features, the framework provides a flexible, data-driven approach to the characterization of urban settlements. The identification of cluster centroids’ dominant attributes enables a systematic interpretation of the spatial distribution of the built environment, while the subsequent mapping process assigns each cluster a descriptive label reflecting the prevailing building fabric. The generated thematic maps yield critical insights into urban morphology and facilitate evidence-based planning. The framework was validated across ten Italian cities selected for their diverse physical, morphological, and historical characteristics; comparisons with the results of urban zone classifications in these cities conducted by experts show that the proposed method provides accurate results, as the similarity to the classifications made by experts, measured by the use of the Adjusted Rand Index, is always higher than or equal to 0.93; furthermore, it is robust when applied in heterogeneous urban settlements. These results confirm the effectiveness of the method in delineating homogeneous urban areas, thereby offering decision makers a robust instrument to guide targeted interventions on existing building stocks. The proposed framework advances the capacity to analyze urban form, to strategically support renovation and urban regeneration policies, and demonstrates a strong potential for portability, as it can be applied to other cities for urban scale analyses. Full article

An Adaptive Neuro-Fuzzy Inference System (ANFIS) framework for paediatric wrist injury classification (fracture versus sprain) was developed utilising infrared thermography (IRT). ANFIS combines artificial neural network (ANN) learning with interpretable fuzzy rules, mitigating the “black-box” limitation of conventional ANNs through explicit membership functions and Takagi–Sugeno rule consequents. Forty children (19 fractures, 21 sprains, confirmed by X-ray radiograph) provided thermal image sequences from which three statistically discriminative temperature distribution features namely standard deviation, inter-quartile range (IQR) and kurtosis were selected. A five-layer Sugeno ANFIS with Gaussian membership functions were trained using a hybrid least-squares/gradient descent optimisation and evaluated under three premise-parameter initialisation strategies: random seeding, K-means clustering, and fuzzy C-means (FCM) data partitioning. Five-fold cross-validation guided the selection of membership functions standard deviation (σ) and rule count, yielding an optimal nine-rule model. Comparative experiments show K-means initialisation achieved the best balance between convergence speed and generalisation versus slower but highly precise random initialisation and rapidly convergent yet unstable FCM. The proposed K-means–driven ANFIS offered data-efficient decision support, highlighting the potential of thermal feature fusion with neuro-fuzzy modelling to reduce unnecessary radiographs in emergency bone fracture triage. Full article

Early and accurate detection of pneumonia from chest X-ray images is essential for improving treatment and clinical outcomes. Medical imaging datasets often exhibit class imbalance and uncertainty in feature extraction, which complicates conventional classification methods and motivates the use of advanced approaches combining deep learning and fuzzy logic. This study proposes a hybrid approach that combines deep learning architectures (VGG16, EfficientNetV2, MobileNetV2, ResNet50) for feature extraction with fuzzy logic-based classifiers, including Fuzzy C-Means, Fuzzy Decision Tree, Fuzzy KNN, Fuzzy SVM, and ANFIS (Adaptive Neuro-Fuzzy Inference System). Feature selection techniques were also applied to enhance the discriminative power of the extracted features. The best-performing model, ANFIS with MobileNetV2 features and Gaussian membership functions, achieved an overall accuracy of 98.52%, with Normal class precision of 97.07%, recall of 97.48%, and F1-score of 97.27%, and Pneumonia class precision of 99.06%, recall of 98.91%, and F1-score of 98.99%. Among the fuzzy classifiers, Fuzzy SVM and Fuzzy KNN also showed strong performance with accuracy above 96%, while Fuzzy Decision Tree and Fuzzy C-Means achieved moderate results. These findings demonstrate that integrating deep feature extraction with neuro-fuzzy reasoning significantly improves diagnostic accuracy and robustness, providing a reliable tool for clinical decision support. Future research will focus on optimizing model efficiency, interpretability, and real-time applicability. Full article

Ancient Chinese scripts—including oracle bone carvings, bronze inscriptions, stone steles, Dunhuang scrolls, and bamboo slips—are rich in historical value but often degraded due to centuries of erosion, damage, and stylistic variability. These issues severely hinder manual transcription and render conventional OCR techniques inadequate, as they are typically trained on modern printed or handwritten text and lack interpretability. To tackle these challenges, we propose FAIR-Net, a hybrid architecture that combines the unsupervised feature learning capacity of a deep autoencoder with the semantic transparency of a fuzzy rule-based classifier. In FAIR-Net, the deep autoencoder first compresses high-resolution character images into low-dimensional, noise-robust embeddings. These embeddings are then passed into a Fuzzy Neural Network (FNN), whose hidden layer leverages Fuzzy C-Means (FCM) clustering to model soft membership degrees and generate human-readable fuzzy rules. The output layer uses Iteratively Reweighted Least Squares Estimation (IRLSE) combined with a Softmax function to produce probabilistic predictions, with all weights constrained as linear mappings to maintain model transparency. We evaluate FAIR-Net on CASIA-HWDB1.0, HWDB1.1, and ICDAR 2013 CompetitionDB, where it achieves a recognition accuracy of 97.91%, significantly outperforming baseline CNNs (p < 0.01, Cohen’s d > 0.8) while maintaining the tightest confidence interval (96.88–98.94%) and lowest standard deviation (±1.03%). Additionally, FAIR-Net reduces inference time to 25 s, improving processing efficiency by 41.9% over AlexNet and up to 98.9% over CNN-Fujitsu, while preserving >97.5% accuracy across evaluations. To further assess generalization to historical scripts, FAIR-Net was tested on the Ancient Chinese Character Dataset (9233 classes; 979,907 images), achieving 83.25% accuracy—slightly higher than ResNet101 but 2.49% lower than SwinT-v2-small—while reducing training time by over 5.5× compared to transformer-based baselines. Fuzzy rule visualization confirms enhanced robustness to glyph ambiguities and erosion. Overall, FAIR-Net provides a practical, interpretable, and highly efficient solution for the digitization and preservation of ancient Chinese character corpora. Full article